Paper Group NANR 149
ULISBOA at SemEval-2016 Task 12: Extraction of temporal expressions, clinical events and relations using IBEnt. Contextual term equivalent search using domain-driven disambiguation. Exploring Distributional Representations and Machine Translation for Aspect-based Cross-lingual Sentiment Classification.. USFD at SemEval-2016 Task 6: Any-Target Stanc …
ULISBOA at SemEval-2016 Task 12: Extraction of temporal expressions, clinical events and relations using IBEnt
| Title | ULISBOA at SemEval-2016 Task 12: Extraction of temporal expressions, clinical events and relations using IBEnt |
| Authors | Marcia Barros, Andre Lamurias, Gon{\c{c}}alo Figueiro, Marta Antunes, Joana Teixeira, Alex Pinheiro, re, Francisco M. Couto |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1196/ |
| https://www.aclweb.org/anthology/S16-1196 | |
| PWC | https://paperswithcode.com/paper/ulisboa-at-semeval-2016-task-12-extraction-of |
| Repo | |
| Framework | |
Contextual term equivalent search using domain-driven disambiguation
| Title | Contextual term equivalent search using domain-driven disambiguation |
| Authors | Caroline Barri{`e}re, Pierre Andr{'e} M{'e}nard, Daphn{'e}e Azoulay |
| Abstract | This article presents a domain-driven algorithm for the task of term sense disambiguation (TSD). TSD aims at automatically choosing which term record from a term bank best represents the meaning of a term occurring in a particular context. In a translation environment, finding the contextually appropriate term record is necessary to access the proper equivalent to be used in the target language text. The term bank TERMIUM Plus, recently published as an open access repository, is chosen as a domain-rich resource for testing our TSD algorithm, using English and French as source and target languages. We devise an experiment using over 1300 English terms found in scientific articles, and show that our domain-driven TSD algorithm is able to bring the best term record, and therefore the best French equivalent, at the average rank of 1.69 compared to a baseline random rank of 3.51. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4704/ |
| https://www.aclweb.org/anthology/W16-4704 | |
| PWC | https://paperswithcode.com/paper/contextual-term-equivalent-search-using |
| Repo | |
| Framework | |
Exploring Distributional Representations and Machine Translation for Aspect-based Cross-lingual Sentiment Classification.
| Title | Exploring Distributional Representations and Machine Translation for Aspect-based Cross-lingual Sentiment Classification. |
| Authors | Jeremy Barnes, Patrik Lambert, Toni Badia |
| Abstract | Cross-lingual sentiment classification (CLSC) seeks to use resources from a source language in order to detect sentiment and classify text in a target language. Almost all research into CLSC has been carried out at sentence and document level, although this level of granularity is often less useful. This paper explores methods for performing aspect-based cross-lingual sentiment classification (aspect-based CLSC) for under-resourced languages. Given the limited nature of parallel data for many languages, we would like to make the most of this resource for our task. We compare zero-shot learning, bilingual word embeddings, stacked denoising autoencoder representations and machine translation techniques for aspect-based CLSC. Each of these approaches requires differing amounts of parallel data. We show that models based on distributed semantics can achieve comparable results to machine translation on aspect-based CLSC and give an analysis of the errors found for each method. |
| Tasks | Denoising, Machine Translation, Sentiment Analysis, Word Embeddings, Zero-Shot Learning |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1152/ |
| https://www.aclweb.org/anthology/C16-1152 | |
| PWC | https://paperswithcode.com/paper/exploring-distributional-representations-and |
| Repo | |
| Framework | |
USFD at SemEval-2016 Task 6: Any-Target Stance Detection on Twitter with Autoencoders
| Title | USFD at SemEval-2016 Task 6: Any-Target Stance Detection on Twitter with Autoencoders |
| Authors | Isabelle Augenstein, Andreas Vlachos, Kalina Bontcheva |
| Abstract | |
| Tasks | Natural Language Inference, Sentiment Analysis, Stance Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1063/ |
| https://www.aclweb.org/anthology/S16-1063 | |
| PWC | https://paperswithcode.com/paper/usfd-at-semeval-2016-task-6-any-target-stance |
| Repo | |
| Framework | |
Lightly Supervised Quality Estimation
| Title | Lightly Supervised Quality Estimation |
| Authors | Matthias Sperber, Graham Neubig, Jan Niehues, Sebastian St{"u}ker, Alex Waibel |
| Abstract | Evaluating the quality of output from language processing systems such as machine translation or speech recognition is an essential step in ensuring that they are sufficient for practical use. However, depending on the practical requirements, evaluation approaches can differ strongly. Often, reference-based evaluation measures (such as BLEU or WER) are appealing because they are cheap and allow rapid quantitative comparison. On the other hand, practitioners often focus on manual evaluation because they must deal with frequently changing domains and quality standards requested by customers, for which reference-based evaluation is insufficient or not possible due to missing in-domain reference data (Harris et al., 2016). In this paper, we attempt to bridge this gap by proposing a framework for lightly supervised quality estimation. We collect manually annotated scores for a small number of segments in a test corpus or document, and combine them with automatically predicted quality scores for the remaining segments to predict an overall quality estimate. An evaluation shows that our framework estimates quality more reliably than using fully automatic quality estimation approaches, while keeping annotation effort low by not requiring full references to be available for the particular domain. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1292/ |
| https://www.aclweb.org/anthology/C16-1292 | |
| PWC | https://paperswithcode.com/paper/lightly-supervised-quality-estimation |
| Repo | |
| Framework | |
Predicting the Evocation Relation between Lexicalized Concepts
| Title | Predicting the Evocation Relation between Lexicalized Concepts |
| Authors | Yoshihiko Hayashi |
| Abstract | Evocation is a directed yet weighted semantic relationship between lexicalized concepts. Although evocation relations are considered potentially useful in several semantic NLP tasks, the prediction of the evocation relation between an arbitrary pair of concepts remains difficult, since evocation relationships cover a broader range of semantic relations rooted in human perception and experience. This paper presents a supervised learning approach to predict the strength (by regression) and to determine the directionality (by classification) of the evocation relation that might hold between a pair of lexicalized concepts. Empirical results that were obtained by investigating useful features are shown, indicating that a combination of the proposed features largely outperformed individual baselines, and also suggesting that semantic relational vectors computed from existing semantic vectors for lexicalized concepts were indeed effective for both the prediction of strength and the determination of directionality. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1156/ |
| https://www.aclweb.org/anthology/C16-1156 | |
| PWC | https://paperswithcode.com/paper/predicting-the-evocation-relation-between |
| Repo | |
| Framework | |
Using Argument Mining to Assess the Argumentation Quality of Essays
| Title | Using Argument Mining to Assess the Argumentation Quality of Essays |
| Authors | Henning Wachsmuth, Khalid Al-Khatib, Benno Stein |
| Abstract | Argument mining aims to determine the argumentative structure of texts. Although it is said to be crucial for future applications such as writing support systems, the benefit of its output has rarely been evaluated. This paper puts the analysis of the output into the focus. In particular, we investigate to what extent the mined structure can be leveraged to assess the argumentation quality of persuasive essays. We find insightful statistical patterns in the structure of essays. From these, we derive novel features that we evaluate in four argumentation-related essay scoring tasks. Our results reveal the benefit of argument mining for assessing argumentation quality. Among others, we improve the state of the art in scoring an essay{'}s organization and its argument strength. |
| Tasks | Argument Mining |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1158/ |
| https://www.aclweb.org/anthology/C16-1158 | |
| PWC | https://paperswithcode.com/paper/using-argument-mining-to-assess-the |
| Repo | |
| Framework | |
ltl.uni-due at SemEval-2016 Task 6: Stance Detection in Social Media Using Stacked Classifiers
| Title | ltl.uni-due at SemEval-2016 Task 6: Stance Detection in Social Media Using Stacked Classifiers |
| Authors | Michael Wojatzki, Torsten Zesch |
| Abstract | |
| Tasks | Stance Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1069/ |
| https://www.aclweb.org/anthology/S16-1069 | |
| PWC | https://paperswithcode.com/paper/ltluni-due-at-semeval-2016-task-6-stance |
| Repo | |
| Framework | |
``Beware the Jabberwock, dear reader!’’ Testing the distributional reality of construction semantics
| Title | ``Beware the Jabberwock, dear reader!’’ Testing the distributional reality of construction semantics | |
| Authors | Gianluca Lebani, Aless Lenci, ro |
| Abstract | Notwithstanding the success of the notion of construction, the computational tradition still lacks a way to represent the semantic content of these linguistic entities. Here we present a simple corpus-based model implementing the idea that the meaning of a syntactic construction is intimately related to the semantics of its typical verbs. It is a two-step process, that starts by identifying the typical verbs occurring with a given syntactic construction and building their distributional vectors. We then calculated the weighted centroid of these vectors in order to derive the distributional signature of a construction. In order to assess the goodness of our approach, we replicated the priming effect described by Johnson and Golberg (2013) as a function of the semantic distance between a construction and its prototypical verbs. Additional support for our view comes from a regression analysis showing that our distributional information can be used to model behavioral data collected with a crowdsourced elicitation experiment. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5302/ |
| https://www.aclweb.org/anthology/W16-5302 | |
| PWC | https://paperswithcode.com/paper/beware-the-jabberwock-dear-reader-testing-the |
| Repo | |
| Framework | |
An Extension of the Slovak Broadcast News Corpus based on Semi-Automatic Annotation
| Title | An Extension of the Slovak Broadcast News Corpus based on Semi-Automatic Annotation |
| Authors | Peter Viszlay, J{'a}n Sta{\v{s}}, Tom{'a}{\v{s}} Koct{'u}r, Martin Lojka, Jozef Juh{'a}r |
| Abstract | In this paper, we introduce an extension of our previously released TUKE-BNews-SK corpus based on a semi-automatic annotation scheme. It firstly relies on the automatic transcription of the BN data performed by our Slovak large vocabulary continuous speech recognition system. The generated hypotheses are then manually corrected and completed by trained human annotators. The corpus is composed of 25 hours of fully-annotated spontaneous and prepared speech. In addition, we have acquired 900 hours of another BN data, part of which we plan to annotate semi-automatically. We present a preliminary corpus evaluation that gives very promising results. |
| Tasks | Large Vocabulary Continuous Speech Recognition, Speech Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1743/ |
| https://www.aclweb.org/anthology/L16-1743 | |
| PWC | https://paperswithcode.com/paper/an-extension-of-the-slovak-broadcast-news |
| Repo | |
| Framework | |
Annotating Topic Development in Information Seeking Queries
| Title | Annotating Topic Development in Information Seeking Queries |
| Authors | Marta Andersson, Adnan {"O}zt{"u}rel, Silvia Pareti |
| Abstract | This paper contributes to the limited body of empirical research in the domain of discourse structure of information seeking queries. We describe the development of an annotation schema for coding topic development in information seeking queries and the initial observations from a pilot sample of query sessions. The main idea that we explore is the relationship between constant and variable discourse entities and their role in tracking changes in the topic progression. We argue that the topicalized entities remain stable across development of the discourse and can be identified by a simple mechanism where anaphora resolution is a precursor. We also claim that a corpus annotated in this framework can be used as training data for dialogue management and computational semantics systems. |
| Tasks | Dialogue Management |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1277/ |
| https://www.aclweb.org/anthology/L16-1277 | |
| PWC | https://paperswithcode.com/paper/annotating-topic-development-in-information |
| Repo | |
| Framework | |
Is an Image Worth More than a Thousand Words? On the Fine-Grain Semantic Differences between Visual and Linguistic Representations
| Title | Is an Image Worth More than a Thousand Words? On the Fine-Grain Semantic Differences between Visual and Linguistic Representations |
| Authors | Guillem Collell, Marie-Francine Moens |
| Abstract | Human concept representations are often grounded with visual information, yet some aspects of meaning cannot be visually represented or are better described with language. Thus, vision and language provide complementary information that, properly combined, can potentially yield more complete concept representations. Recently, state-of-the-art distributional semantic models and convolutional neural networks have achieved great success in representing linguistic and visual knowledge respectively. In this paper, we compare both, visual and linguistic representations in their ability to capture different types of fine-grain semantic knowledge{—}or attributes{—}of concepts. Humans often describe objects using attributes, that is, properties such as shape, color or functionality, which often transcend the linguistic and visual modalities. In our setting, we evaluate how well attributes can be predicted by using the unimodal representations as inputs. We are interested in first, finding out whether attributes are generally better captured by either the vision or by the language modality; and second, if none of them is clearly superior (as we hypothesize), what type of attributes or semantic knowledge are better encoded from each modality. Ultimately, our study sheds light on the potential of combining visual and textual representations. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1264/ |
| https://www.aclweb.org/anthology/C16-1264 | |
| PWC | https://paperswithcode.com/paper/is-an-image-worth-more-than-a-thousand-words |
| Repo | |
| Framework | |
Topic-Informed Neural Machine Translation
| Title | Topic-Informed Neural Machine Translation |
| Authors | Jian Zhang, Liangyou Li, Andy Way, Qun Liu |
| Abstract | In recent years, neural machine translation (NMT) has demonstrated state-of-the-art machine translation (MT) performance. It is a new approach to MT, which tries to learn a set of parameters to maximize the conditional probability of target sentences given source sentences. In this paper, we present a novel approach to improve the translation performance in NMT by conveying topic knowledge during translation. The proposed topic-informed NMT can increase the likelihood of selecting words from the same topic and domain for translation. Experimentally, we demonstrate that topic-informed NMT can achieve a 1.15 (3.3{%} relative) and 1.67 (5.4{%} relative) absolute improvement in BLEU score on the Chinese-to-English language pair using NIST 2004 and 2005 test sets, respectively, compared to NMT without topic information. |
| Tasks | Machine Translation, Topic Models |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1170/ |
| https://www.aclweb.org/anthology/C16-1170 | |
| PWC | https://paperswithcode.com/paper/topic-informed-neural-machine-translation |
| Repo | |
| Framework | |
Off-topic Response Detection for Spontaneous Spoken English Assessment
| Title | Off-topic Response Detection for Spontaneous Spoken English Assessment |
| Authors | Andrey Malinin, Rogier Van Dalen, Kate Knill, Yu Wang, Mark Gales |
| Abstract | |
| Tasks | Semantic Textual Similarity, Speech Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1102/ |
| https://www.aclweb.org/anthology/P16-1102 | |
| PWC | https://paperswithcode.com/paper/off-topic-response-detection-for-spontaneous |
| Repo | |
| Framework | |
A Meaning-based English Math Word Problem Solver with Understanding, Reasoning and Explanation
| Title | A Meaning-based English Math Word Problem Solver with Understanding, Reasoning and Explanation |
| Authors | Chao-Chun Liang, Shih-Hong Tsai, Ting-Yun Chang, Yi-Chung Lin, Keh-Yih Su |
| Abstract | This paper presents a meaning-based statistical math word problem (MWP) solver with understanding, reasoning and explanation. It comprises a web user interface and pipelined modules for analysing the text, transforming both body and question parts into their logic forms, and then performing inference on them. The associated context of each quantity is represented with proposed role-tags (e.g., nsubj, verb, etc.), which provides the flexibility for annotating the extracted math quantity with its associated syntactic and semantic information (which specifies the physical meaning of that quantity). Those role-tags are then used to identify the desired operands and filter out irrelevant quantities (so that the answer can be obtained precisely). Since the physical meaning of each quantity is explicitly represented with those role-tags and used in the inference process, the proposed approach could explain how the answer is obtained in a human comprehensible way. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2032/ |
| https://www.aclweb.org/anthology/C16-2032 | |
| PWC | https://paperswithcode.com/paper/a-meaning-based-english-math-word-problem |
| Repo | |
| Framework | |
