Paper Group NANR 44
An Online Sequence-to-Sequence Model Using Partial Conditioning. Learning Tone and Attribution for Financial Text Mining. Concept Grounding to Multiple Knowledge Bases via Indirect Supervision. Modelling the informativeness and timing of non-verbal cues in parent-child interaction. Comparing the Level of Code-Switching in Corpora. An Hymn of an eve …
An Online Sequence-to-Sequence Model Using Partial Conditioning
| Title | An Online Sequence-to-Sequence Model Using Partial Conditioning |
| Authors | Navdeep Jaitly, Quoc V. Le, Oriol Vinyals, Ilya Sutskever, David Sussillo, Samy Bengio |
| Abstract | Sequence-to-sequence models have achieved impressive results on various tasks. However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output sequences. This is because they generate an output sequence conditioned on an entire input sequence. In this paper, we present a Neural Transducer that can make incremental predictions as more input arrives, without redoing the entire computation. Unlike sequence-to-sequence models, the Neural Transducer computes the next-step distribution conditioned on the partially observed input sequence and the partially generated sequence. At each time step, the transducer can decide to emit zero to many output symbols. The data can be processed using an encoder and presented as input to the transducer. The discrete decision to emit a symbol at every time step makes it difficult to learn with conventional backpropagation. It is however possible to train the transducer by using a dynamic programming algorithm to generate target discrete decisions. Our experiments show that the Neural Transducer works well in settings where it is required to produce output predictions as data come in. We also find that the Neural Transducer performs well for long sequences even when attention mechanisms are not used. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6594-an-online-sequence-to-sequence-model-using-partial-conditioning |
| http://papers.nips.cc/paper/6594-an-online-sequence-to-sequence-model-using-partial-conditioning.pdf | |
| PWC | https://paperswithcode.com/paper/an-online-sequence-to-sequence-model-using |
| Repo | |
| Framework | |
Learning Tone and Attribution for Financial Text Mining
| Title | Learning Tone and Attribution for Financial Text Mining |
| Authors | Mahmoud El-Haj, Paul Rayson, Steve Young, Andrew Moore, Martin Walker, Thomas Schleicher, Vasiliki Athanasakou |
| Abstract | Attribution bias refers to the tendency of people to attribute successes to their own abilities but failures to external factors. In a business context an internal factor might be the restructuring of the firm and an external factor might be an unfavourable change in exchange or interest rates. In accounting research, the presence of an attribution bias has been demonstrated for the narrative sections of the annual financial reports. Previous studies have applied manual content analysis to this problem but in this paper we present novel work to automate the analysis of attribution bias through using machine learning algorithms. Previous studies have only applied manual content analysis on a small scale to reveal such a bias in the narrative section of annual financial reports. In our work a group of experts in accounting and finance labelled and annotated a list of 32,449 sentences from a random sample of UK Preliminary Earning Announcements (PEAs) to allow us to examine whether sentences in PEAs contain internal or external attribution and which kinds of attributions are linked to positive or negative performance. We wished to examine whether human annotators could agree on coding this difficult task and whether Machine Learning (ML) could be applied reliably to replicate the coding process on a much larger scale. Our best machine learning algorithm correctly classified performance sentences with 70{%} accuracy and detected tone and attribution in financial PEAs with accuracy of 79{%}. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1287/ |
| https://www.aclweb.org/anthology/L16-1287 | |
| PWC | https://paperswithcode.com/paper/learning-tone-and-attribution-for-financial |
| Repo | |
| Framework | |
Concept Grounding to Multiple Knowledge Bases via Indirect Supervision
| Title | Concept Grounding to Multiple Knowledge Bases via Indirect Supervision |
| Authors | Chen-Tse Tsai, Dan Roth |
| Abstract | We consider the problem of disambiguating concept mentions appearing in documents and grounding them in multiple knowledge bases, where each knowledge base addresses some aspects of the domain. This problem poses a few additional challenges beyond those addressed in the popular Wikification problem. Key among them is that most knowledge bases do not contain the rich textual and structural information Wikipedia does; consequently, the main supervision signal used to train Wikification rankers does not exist anymore. In this work we develop an algorithmic approach that, by carefully examining the relations between various related knowledge bases, generates an indirect supervision signal it uses to train a ranking model that accurately chooses knowledge base entries for a given mention; moreover, it also induces prior knowledge that can be used to support a global coherent mapping of all the concepts in a given document to the knowledge bases. Using the biomedical domain as our application, we show that our indirectly supervised ranking model outperforms other unsupervised baselines and that the quality of this indirect supervision scheme is very close to a supervised model. We also show that considering multiple knowledge bases together has an advantage over grounding concepts to each knowledge base individually. |
| Tasks | Entity Linking |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1011/ |
| https://www.aclweb.org/anthology/Q16-1011 | |
| PWC | https://paperswithcode.com/paper/concept-grounding-to-multiple-knowledge-bases |
| Repo | |
| Framework | |
Modelling the informativeness and timing of non-verbal cues in parent-child interaction
| Title | Modelling the informativeness and timing of non-verbal cues in parent-child interaction |
| Authors | Kristina Nilsson Bj{"o}rkenstam, Mats Wir{'e}n, Robert {"O}stling |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1911/ |
| https://www.aclweb.org/anthology/W16-1911 | |
| PWC | https://paperswithcode.com/paper/modelling-the-informativeness-and-timing-of |
| Repo | |
| Framework | |
Comparing the Level of Code-Switching in Corpora
| Title | Comparing the Level of Code-Switching in Corpora |
| Authors | Bj{"o}rn Gamb{"a}ck, Amitava Das |
| Abstract | Social media texts are often fairly informal and conversational, and when produced by bilinguals tend to be written in several different languages simultaneously, in the same way as conversational speech. The recent availability of large social media corpora has thus also made large-scale code-switched resources available for research. The paper addresses the issues of evaluation and comparison these new corpora entail, by defining an objective measure of corpus level complexity of code-switched texts. It is also shown how this formal measure can be used in practice, by applying it to several code-switched corpora. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1292/ |
| https://www.aclweb.org/anthology/L16-1292 | |
| PWC | https://paperswithcode.com/paper/comparing-the-level-of-code-switching-in |
| Repo | |
| Framework | |
An Hymn of an even Deeper Sentiment Analysis
| Title | An Hymn of an even Deeper Sentiment Analysis |
| Authors | Manfred Klenner |
| Abstract | |
| Tasks | Common Sense Reasoning, Semantic Role Labeling, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0426/ |
| https://www.aclweb.org/anthology/W16-0426 | |
| PWC | https://paperswithcode.com/paper/an-hymn-of-an-even-deeper-sentiment-analysis |
| Repo | |
| Framework | |
Generating Training Data for Semantic Role Labeling based on Label Transfer from Linked Lexical Resources
| Title | Generating Training Data for Semantic Role Labeling based on Label Transfer from Linked Lexical Resources |
| Authors | Silvana Hartmann, Judith Eckle-Kohler, Iryna Gurevych |
| Abstract | We present a new approach for generating role-labeled training data using Linked Lexical Resources, i.e., integrated lexical resources that combine several resources (e.g., Word-Net, FrameNet, Wiktionary) by linking them on the sense or on the role level. Unlike resource-based supervision in relation extraction, we focus on complex linguistic annotations, more specifically FrameNet senses and roles. The automatically labeled training data (www.ukp.tu-darmstadt.de/knowledge-based-srl/) are evaluated on four corpora from different domains for the tasks of word sense disambiguation and semantic role classification. Results show that classifiers trained on our generated data equal those resulting from a standard supervised setting. |
| Tasks | Machine Translation, Question Answering, Reading Comprehension, Relation Extraction, Semantic Role Labeling, Word Sense Disambiguation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1015/ |
| https://www.aclweb.org/anthology/Q16-1015 | |
| PWC | https://paperswithcode.com/paper/generating-training-data-for-semantic-role |
| Repo | |
| Framework | |
Cross-Lingual Lexico-Semantic Transfer in Language Learning
| Title | Cross-Lingual Lexico-Semantic Transfer in Language Learning |
| Authors | Ekaterina Kochmar, Ekaterina Shutova |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1092/ |
| https://www.aclweb.org/anthology/P16-1092 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-lexico-semantic-transfer-in |
| Repo | |
| Framework | |
SCARE ― The Sentiment Corpus of App Reviews with Fine-grained Annotations in German
| Title | SCARE ― The Sentiment Corpus of App Reviews with Fine-grained Annotations in German |
| Authors | Mario S{"a}nger, Ulf Leser, Steffen Kemmerer, Peter Adolphs, Roman Klinger |
| Abstract | The automatic analysis of texts containing opinions of users about, e.g., products or political views has gained attention within the last decades. However, previous work on the task of analyzing user reviews about mobile applications in app stores is limited. Publicly available corpora do not exist, such that a comparison of different methods and models is difficult. We fill this gap by contributing the Sentiment Corpus of App Reviews (SCARE), which contains fine-grained annotations of application aspects, subjective (evaluative) phrases and relations between both. This corpus consists of 1,760 annotated application reviews from the Google Play Store with 2,487 aspects and 3,959 subjective phrases. We describe the process and methodology how the corpus was created. The Fleiss Kappa between four annotators reveals an agreement of 0.72. We provide a strong baseline with a linear-chain conditional random field and word-embedding features with a performance of 0.62 for aspect detection and 0.63 for the extraction of subjective phrases. The corpus is available to the research community to support the development of sentiment analysis methods on mobile application reviews. |
| Tasks | Sentiment Analysis |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1178/ |
| https://www.aclweb.org/anthology/L16-1178 | |
| PWC | https://paperswithcode.com/paper/scare-a-the-sentiment-corpus-of-app-reviews |
| Repo | |
| Framework | |
Rev at SemEval-2016 Task 2: Aligning Chunks by Lexical, Part of Speech and Semantic Equivalence
| Title | Rev at SemEval-2016 Task 2: Aligning Chunks by Lexical, Part of Speech and Semantic Equivalence |
| Authors | Ping Tan, Karin Verspoor, Timothy Miller |
| Abstract | |
| Tasks | Semantic Textual Similarity |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1120/ |
| https://www.aclweb.org/anthology/S16-1120 | |
| PWC | https://paperswithcode.com/paper/rev-at-semeval-2016-task-2-aligning-chunks-by |
| Repo | |
| Framework | |
AUEB-ABSA at SemEval-2016 Task 5: Ensembles of Classifiers and Embeddings for Aspect Based Sentiment Analysis
| Title | AUEB-ABSA at SemEval-2016 Task 5: Ensembles of Classifiers and Embeddings for Aspect Based Sentiment Analysis |
| Authors | Dionysios Xenos, Panagiotis Theodorakakos, John Pavlopoulos, Prodromos Malakasiotis, Ion Androutsopoulos |
| Abstract | |
| Tasks | Aspect-Based Sentiment Analysis, Opinion Mining, Sentiment Analysis, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1050/ |
| https://www.aclweb.org/anthology/S16-1050 | |
| PWC | https://paperswithcode.com/paper/aueb-absa-at-semeval-2016-task-5-ensembles-of |
| Repo | |
| Framework | |
Name Variation in Community Question Answering Systems
| Title | Name Variation in Community Question Answering Systems |
| Authors | Anietie Andy, Satoshi Sekine, Mugizi Rwebangira, Mark Dredze |
| Abstract | Name Variation in Community Question Answering Systems Abstract Community question answering systems are forums where users can ask and answer questions in various categories. Examples are Yahoo! Answers, Quora, and Stack Overflow. A common challenge with such systems is that a significant percentage of asked questions are left unanswered. In this paper, we propose an algorithm to reduce the number of unanswered questions in Yahoo! Answers by reusing the answer to the most similar past resolved question to the unanswered question, from the site. Semantically similar questions could be worded differently, thereby making it difficult to find questions that have shared needs. For example, {}Who is the best player for the Reds?{''} and {}Who is currently the biggest star at Manchester United?{''} have a shared need but are worded differently; also, {}Reds{''} and {}Manchester United{''} are used to refer to the soccer team Manchester United football club. In this research, we focus on question categories that contain a large number of named entities and entity name variations. We show that in these categories, entity linking can be used to identify relevant past resolved questions with shared needs as a given question by disambiguating named entities and matching these questions based on the disambiguated entities, identified entities, and knowledge base information related to these entities. We evaluated our algorithm on a new dataset constructed from Yahoo! Answers. The dataset contains annotated question pairs, (Qgiven, [Qpast, Answer]). We carried out experiments on several question categories and show that an entity-based approach gives good performance when searching for similar questions in entity rich categories. |
| Tasks | Community Question Answering, Entity Linking, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-3909/ |
| https://www.aclweb.org/anthology/W16-3909 | |
| PWC | https://paperswithcode.com/paper/name-variation-in-community-question |
| Repo | |
| Framework | |
Comparing Apples to Apple: The Effects of Stemmers on Topic Models
| Title | Comparing Apples to Apple: The Effects of Stemmers on Topic Models |
| Authors | Alex Schofield, ra, David Mimno |
| Abstract | Rule-based stemmers such as the Porter stemmer are frequently used to preprocess English corpora for topic modeling. In this work, we train and evaluate topic models on a variety of corpora using several different stemming algorithms. We examine several different quantitative measures of the resulting models, including likelihood, coherence, model stability, and entropy. Despite their frequent use in topic modeling, we find that stemmers produce no meaningful improvement in likelihood and coherence and in fact can degrade topic stability. |
| Tasks | Information Retrieval, Semantic Textual Similarity, Topic Models |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1021/ |
| https://www.aclweb.org/anthology/Q16-1021 | |
| PWC | https://paperswithcode.com/paper/comparing-apples-to-apple-the-effects-of |
| Repo | |
| Framework | |
Multilingual Projection for Parsing Truly Low-Resource Languages
| Title | Multilingual Projection for Parsing Truly Low-Resource Languages |
| Authors | {\v{Z}}eljko Agi{'c}, Anders Johannsen, Barbara Plank, H{'e}ctor Mart{'\i}nez Alonso, Natalie Schluter, Anders S{\o}gaard |
| Abstract | We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages. Our annotation projection-based approach yields tagging and parsing models for over 100 languages. All that is needed are freely available parallel texts, and taggers and parsers for resource-rich languages. The empirical evaluation across 30 test languages shows that our method consistently provides top-level accuracies, close to established upper bounds, and outperforms several competitive baselines. |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Part-Of-Speech Tagging, Tokenization, Transfer Learning |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1022/ |
| https://www.aclweb.org/anthology/Q16-1022 | |
| PWC | https://paperswithcode.com/paper/multilingual-projection-for-parsing-truly-low |
| Repo | |
| Framework | |
Generating Clinically Relevant Texts: A Case Study on Life-Changing Events
| Title | Generating Clinically Relevant Texts: A Case Study on Life-Changing Events |
| Authors | Mayuresh Oak, Anil Behera, Titus Thomas, Cecilia Ovesdotter Alm, Emily Prud{'}hommeaux, Christopher Homan, Raymond Ptucha |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0309/ |
| https://www.aclweb.org/anthology/W16-0309 | |
| PWC | https://paperswithcode.com/paper/generating-clinically-relevant-texts-a-case |
| Repo | |
| Framework | |
