Paper Group NANR 141
Leveraging syntactic parsing to improve event annotation matching. Automatic Detection of Translation Direction. HITS-SBD at the FinSBD Task: Machine Learning vs. Rule-based Sentence Boundary Detection. Differences between SMT and NMT Output - a Translators’ Point of View. JRC TMA-CC: Slavic Named Entity Recognition and Linking. Participation in th …
Leveraging syntactic parsing to improve event annotation matching
| Title | Leveraging syntactic parsing to improve event annotation matching |
| Authors | Camiel Colruyt, Orph{'e}e De Clercq, V{'e}ronique Hoste |
| Abstract | Detecting event mentions is the first step in event extraction from text and annotating them is a notoriously difficult task. Evaluating annotator consistency is crucial when building datasets for mention detection. When event mentions are allowed to cover many tokens, annotators may disagree on their span, which means that overlapping annotations may then refer to the same event or to different events. This paper explores different fuzzy-matching functions which aim to resolve this ambiguity. The functions extract the sets of syntactic heads present in the annotations, use the Dice coefficient to measure the similarity between sets and return a judgment based on a given threshold. The functions are tested against the judgment of a human evaluator and a comparison is made between sets of tokens and sets of syntactic heads. The best-performing function is a head-based function that is found to agree with the human evaluator in 89{%} of cases. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5903/ |
| https://www.aclweb.org/anthology/D19-5903 | |
| PWC | https://paperswithcode.com/paper/leveraging-syntactic-parsing-to-improve-event |
| Repo | |
| Framework | |
Automatic Detection of Translation Direction
| Title | Automatic Detection of Translation Direction |
| Authors | Ilia Sominsky, Shuly Wintner |
| Abstract | Parallel corpora are crucial resources for NLP applications, most notably for machine translation. The direction of the (human) translation of parallel corpora has been shown to have significant implications for the quality of statistical machine translation systems that are trained with such corpora. We describe a method for determining the direction of the (manual) translation of parallel corpora at the sentence-pair level. Using several linguistically-motivated features, coupled with a neural network model, we obtain high accuracy on several language pairs. Furthermore, we demonstrate that the accuracy is correlated with the (typological) distance between the two languages. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1130/ |
| https://www.aclweb.org/anthology/R19-1130 | |
| PWC | https://paperswithcode.com/paper/automatic-detection-of-translation-direction |
| Repo | |
| Framework | |
HITS-SBD at the FinSBD Task: Machine Learning vs. Rule-based Sentence Boundary Detection
| Title | HITS-SBD at the FinSBD Task: Machine Learning vs. Rule-based Sentence Boundary Detection |
| Authors | Mehwish Fatima, Mark-Christoph Mueller |
| Abstract | |
| Tasks | Boundary Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5520/ |
| https://www.aclweb.org/anthology/W19-5520 | |
| PWC | https://paperswithcode.com/paper/hits-sbd-at-the-finsbd-task-machine-learning |
| Repo | |
| Framework | |
Differences between SMT and NMT Output - a Translators’ Point of View
| Title | Differences between SMT and NMT Output - a Translators’ Point of View |
| Authors | Jonathan Mutal, Lise Volkart, Pierrette Bouillon, Sabrina Girletti, Paula Estrella |
| Abstract | In this study, we compare the output quality of two MT systems, a statistical (SMT) and a neural (NMT) engine, customised for Swiss Post{'}s Language Service using the same training data. We focus on the point of view of professional translators and investigate how they perceive the differences between the MT output and a human reference (namely deletions, substitutions, insertions and word order). Our findings show that translators more frequently consider these differences to be errors in SMT than NMT, and that deletions are the most serious errors in both architectures. We also observe lower agreement on differences to be corrected in NMT than in SMT, suggesting that errors are easier to identify in SMT. These findings confirm the ability of NMT to produce correct paraphrases, which could also explain why BLEU is often considered as an inadequate metric to evaluate the performance of NMT systems. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8709/ |
| https://www.aclweb.org/anthology/W19-8709 | |
| PWC | https://paperswithcode.com/paper/differences-between-smt-and-nmt-output-a |
| Repo | |
| Framework | |
JRC TMA-CC: Slavic Named Entity Recognition and Linking. Participation in the BSNLP-2019 shared task
| Title | JRC TMA-CC: Slavic Named Entity Recognition and Linking. Participation in the BSNLP-2019 shared task |
| Authors | Guillaume Jacquet, Jakub Piskorski, Hristo Tanev, Ralf Steinberger |
| Abstract | We report on the participation of the JRC Text Mining and Analysis Competence Centre (TMA-CC) in the BSNLP-2019 Shared Task, which focuses on named-entity recognition, lemmatisation and cross-lingual linking. We propose a hybrid system combining a rule-based approach and light ML techniques. We use multilingual lexical resources such as JRC-NAMES and BABELNET together with a named entity guesser to recognise names. In a second step, we combine known names with wild cards to increase recognition recall by also capturing inflection variants. In a third step, we increase precision by filtering these name candidates with automatically learnt inflection patterns derived from name occurrences in large news article collections. Our major requirement is to achieve high precision. We achieved an average of 65{%} F-measure with 93{%} precision on the four languages. |
| Tasks | Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3714/ |
| https://www.aclweb.org/anthology/W19-3714 | |
| PWC | https://paperswithcode.com/paper/jrc-tma-cc-slavic-named-entity-recognition |
| Repo | |
| Framework | |
Discourse Representation Parsing for Sentences and Documents
| Title | Discourse Representation Parsing for Sentences and Documents |
| Authors | Jiangming Liu, Shay B. Cohen, Mirella Lapata |
| Abstract | We introduce a novel semantic parsing task based on Discourse Representation Theory (DRT; Kamp and Reyle 1993). Our model operates over Discourse Representation Tree Structures which we formally define for sentences and documents. We present a general framework for parsing discourse structures of arbitrary length and granularity. We achieve this with a neural model equipped with a supervised hierarchical attention mechanism and a linguistically-motivated copy strategy. Experimental results on sentence- and document-level benchmarks show that our model outperforms competitive baselines by a wide margin. |
| Tasks | Semantic Parsing |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1629/ |
| https://www.aclweb.org/anthology/P19-1629 | |
| PWC | https://paperswithcode.com/paper/discourse-representation-parsing-for |
| Repo | |
| Framework | |
SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network
| Title | SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network |
| Authors | Asma Atamna, Nataliya Sokolovska, Jean-Claude Crivello |
| Abstract | A wide range of machine learning problems involve handling graph-structured data. Existing machine learning approaches for graphs, however, often imply computing expensive graph similarity measures, preprocessing input graphs, or explicitly ordering graph nodes. In this work, we present a novel and simple convolutional neural network architecture for supervised learning on graphs that is provably invariant to node permutation. The proposed architecture operates directly on arbitrary graphs and performs no node sorting. It also uses a simple multi-layer perceptron for prediction as opposed to conventional convolution layers commonly used in other deep learning approaches for graphs. Despite its simplicity, our architecture is competitive with state-of-the-art graph kernels and existing graph neural networks on benchmark graph classification data sets. Our approach clearly outperforms other deep learning algorithms for graphs on multiple multiclass classification tasks. We also evaluate our approach on a real-world original application in materials science, on which we achieve extremely reasonable results. |
| Tasks | Graph Classification, Graph Similarity |
| Published | 2019-04-08 |
| URL | https://hal.archives-ouvertes.fr/hal-02093451/ |
| https://hal.archives-ouvertes.fr/hal-02093451/document | |
| PWC | https://paperswithcode.com/paper/spi-gcn-a-simple-permutation-invariant-graph |
| Repo | |
| Framework | |
Neural Self-Training through Spaced Repetition
| Title | Neural Self-Training through Spaced Repetition |
| Authors | Hadi Amiri |
| Abstract | Self-training is a semi-supervised learning approach for utilizing unlabeled data to create better learners. The efficacy of self-training algorithms depends on their data sampling techniques. The majority of current sampling techniques are based on predetermined policies which may not effectively explore the data space or improve model generalizability. In this work, we tackle the above challenges by introducing a new data sampling technique based on spaced repetition that dynamically samples informative and diverse unlabeled instances with respect to individual learner and instance characteristics. The proposed model is specifically effective in the context of neural models which can suffer from overfitting and high-variance gradients when trained with small amount of labeled data. Our model outperforms current semi-supervised learning approaches developed for neural networks on publicly-available datasets. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1003/ |
| https://www.aclweb.org/anthology/N19-1003 | |
| PWC | https://paperswithcode.com/paper/neural-self-training-through-spaced |
| Repo | |
| Framework | |
FiST – towards a free Semantic Tagger of modern standard Finnish
| Title | FiST – towards a free Semantic Tagger of modern standard Finnish |
| Authors | Kimmo Kettunen |
| Abstract | |
| Tasks | Morphological Analysis |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0306/ |
| https://www.aclweb.org/anthology/W19-0306 | |
| PWC | https://paperswithcode.com/paper/fist-extendash-towards-a-free-semantic-tagger |
| Repo | |
| Framework | |
DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization
| Title | DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization |
| Authors | Chujie Lu, Long Chen, Chilie Tan, Xiaolin Li, Jun Xiao |
| Abstract | In this paper, we focus on natural language video localization: localizing (ie, grounding) a natural language description in a long and untrimmed video sequence. All currently published models for addressing this problem can be categorized into two types: (i) top-down approach: it does classification and regression for a set of pre-cut video segment candidates; (ii) bottom-up approach: it directly predicts probabilities for each video frame as the temporal boundaries (ie, start and end time point). However, both two approaches suffer several limitations: the former is computation-intensive for densely placed candidates, while the latter has trailed the performance of the top-down counterpart thus far. To this end, we propose a novel dense bottom-up framework: DEnse Bottom-Up Grounding (DEBUG). DEBUG regards all frames falling in the ground truth segment as foreground, and each foreground frame regresses the unique distances from its location to bi-directional ground truth boundaries. Extensive experiments on three challenging benchmarks (TACoS, Charades-STA, and ActivityNet Captions) show that DEBUG is able to match the speed of bottom-up models while surpassing the performance of the state-of-the-art top-down models. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1518/ |
| https://www.aclweb.org/anthology/D19-1518 | |
| PWC | https://paperswithcode.com/paper/debug-a-dense-bottom-up-grounding-approach |
| Repo | |
| Framework | |
Investigating CNNs’ Learning Representation under label noise
| Title | Investigating CNNs’ Learning Representation under label noise |
| Authors | Ryuichiro Hataya, Hideki Nakayama |
| Abstract | Deep convolutional neural networks (CNNs) are known to be robust against label noise on extensive datasets. However, at the same time, CNNs are capable of memorizing all labels even if they are random, which means they can memorize corrupted labels. Are CNNs robust or fragile to label noise? Much of researches focusing on such memorization uses class-independent label noise to simulate label corruption, but this setting is simple and unrealistic. In this paper, we investigate the behavior of CNNs under class-dependently simulated label noise, which is generated based on the conceptual distance between classes of a large dataset (i.e., ImageNet-1k). Contrary to previous knowledge, we reveal CNNs are more robust to such class-dependent label noise than class-independent label noise. We also demonstrate the networks under class-dependent noise situations learn similar representation to the no noise situation, compared to class-independent noise situations. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1xmqiAqFm |
| https://openreview.net/pdf?id=H1xmqiAqFm | |
| PWC | https://paperswithcode.com/paper/investigating-cnns-learning-representation |
| Repo | |
| Framework | |
Towards discourse annotation and sentiment analysis of the Basque Opinion Corpus
| Title | Towards discourse annotation and sentiment analysis of the Basque Opinion Corpus |
| Authors | Jon Alkorta, Koldo Gojenola, Mikel Iruskieta |
| Abstract | Discourse information is crucial for a better understanding of the text structure and it is also necessary to describe which part of an opinionated text is more relevant or to decide how a text span can change the polarity (strengthen or weaken) of other span by means of coherence relations. This work presents the first results on the annotation of the Basque Opinion Corpus using Rhetorical Structure Theory (RST). Our evaluation results and analysis show us the main avenues to improve on a future annotation process. We have also extracted the subjectivity of several rhetorical relations and the results show the effect of sentiment words in relations and the influence of each relation in the semantic orientation value. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2718/ |
| https://www.aclweb.org/anthology/W19-2718 | |
| PWC | https://paperswithcode.com/paper/towards-discourse-annotation-and-sentiment |
| Repo | |
| Framework | |
What do phone embeddings learn about Phonology?
| Title | What do phone embeddings learn about Phonology? |
| Authors | Sudheer Kolachina, Lilla Magyar |
| Abstract | Recent work has looked at evaluation of phone embeddings using sound analogies and correlations between distinctive feature space and embedding space. It has not been clear what aspects of natural language phonology are learnt by neural network inspired distributed representational models such as word2vec. To study the kinds of phonological relationships learnt by phone embeddings, we present artificial phonology experiments that show that phone embeddings learn paradigmatic relationships such as phonemic and allophonic distribution quite well. They are also able to capture co-occurrence restrictions among vowels such as those observed in languages with vowel harmony. However, they are unable to learn co-occurrence restrictions among the class of consonants. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4219/ |
| https://www.aclweb.org/anthology/W19-4219 | |
| PWC | https://paperswithcode.com/paper/what-do-phone-embeddings-learn-about |
| Repo | |
| Framework | |
SenZi: A Sentiment Analysis Lexicon for the Latinised Arabic (Arabizi)
| Title | SenZi: A Sentiment Analysis Lexicon for the Latinised Arabic (Arabizi) |
| Authors | Taha Tobaili, Fern, Miriam ez, Harith Alani, Sanaa Sharafeddine, Hazem Hajj, Goran Glava{\v{s}} |
| Abstract | Arabizi is an informal written form of dialectal Arabic transcribed in Latin alphanumeric characters. It has a proven popularity on chat platforms and social media, yet it suffers from a severe lack of natural language processing (NLP) resources. As such, texts written in Arabizi are often disregarded in sentiment analysis tasks for Arabic. In this paper we describe the creation of a sentiment lexicon for Arabizi that was enriched with word embeddings. The result is a new Arabizi lexicon consisting of 11.3K positive and 13.3K negative words. We evaluated this lexicon by classifying the sentiment of Arabizi tweets achieving an F1-score of 0.72. We provide a detailed error analysis to present the challenges that impact the sentiment analysis of Arabizi. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1138/ |
| https://www.aclweb.org/anthology/R19-1138 | |
| PWC | https://paperswithcode.com/paper/senzi-a-sentiment-analysis-lexicon-for-the |
| Repo | |
| Framework | |
Extracting Common Inference Patterns from Semi-Structured Explanations
| Title | Extracting Common Inference Patterns from Semi-Structured Explanations |
| Authors | Sebastian Thiem, Peter Jansen |
| Abstract | Complex questions often require combining multiple facts to correctly answer, particularly when generating detailed explanations for why those answers are correct. Combining multiple facts to answer questions is often modeled as a {}multi-hop{''} graph traversal problem, where a given solver must find a series of interconnected facts in a knowledge graph that, taken together, answer the question and explain the reasoning behind that answer. Multi-hop inference currently suffers from semantic drift, or the tendency for chains of reasoning to {}drift{''}{'} to unrelated topics, and this semantic drift greatly limits the number of facts that can be combined in both free text or knowledge base inference. In this work we present our effort to mitigate semantic drift by extracting large high-confidence multi-hop inference patterns, generated by abstracting large-scale explanatory structure from a corpus of detailed explanations. We represent these inference patterns as sets of generalized constraints over sentences represented as rows in a knowledge base of semi-structured tables. We present a prototype tool for identifying common inference patterns from corpora of semi-structured explanations, and use it to successfully extract 67 inference patterns from a {``}matter{''} subset of standardized elementary science exam questions that span scientific and world knowledge. | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6006/ |
| https://www.aclweb.org/anthology/D19-6006 | |
| PWC | https://paperswithcode.com/paper/extracting-common-inference-patterns-from |
| Repo | |
| Framework | |
