Paper Group NANR 147
Exploring Differential Topic Models for Comparative Summarization of Scientific Papers. Towards Semantic-based Hybrid Machine Translation between Bulgarian and English. Combining syntactic patterns and Wikipedia’s hierarchy of hyperlinks to extract meronym relations. Natural Language Generation through Character-based RNNs with Finite-state Prior K …
Exploring Differential Topic Models for Comparative Summarization of Scientific Papers
| Title | Exploring Differential Topic Models for Comparative Summarization of Scientific Papers |
| Authors | Lei He, Wei Li, Hai Zhuge |
| Abstract | This paper investigates differential topic models (dTM) for summarizing the differences among document groups. Starting from a simple probabilistic generative model, we propose dTM-SAGE that explicitly models the deviations on group-specific word distributions to indicate how words are used differen-tially across different document groups from a background word distribution. It is more effective to capture unique characteristics for comparing document groups. To generate dTM-based comparative summaries, we propose two sentence scoring methods for measuring the sentence discriminative capacity. Experimental results on scientific papers dataset show that our dTM-based comparative summari-zation methods significantly outperform the generic baselines and the state-of-the-art comparative summarization methods under ROUGE metrics. |
| Tasks | Sentiment Analysis, Topic Models |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1098/ |
| https://www.aclweb.org/anthology/C16-1098 | |
| PWC | https://paperswithcode.com/paper/exploring-differential-topic-models-for |
| Repo | |
| Framework | |
Towards Semantic-based Hybrid Machine Translation between Bulgarian and English
| Title | Towards Semantic-based Hybrid Machine Translation between Bulgarian and English |
| Authors | Kiril Simov, Petya Osenova, Alex Popov, er |
| Abstract | |
| Tasks | Common Sense Reasoning, Language Modelling, Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0604/ |
| https://www.aclweb.org/anthology/W16-0604 | |
| PWC | https://paperswithcode.com/paper/towards-semantic-based-hybrid-machine |
| Repo | |
| Framework | |
Combining syntactic patterns and Wikipedia’s hierarchy of hyperlinks to extract meronym relations
| Title | Combining syntactic patterns and Wikipedia’s hierarchy of hyperlinks to extract meronym relations |
| Authors | Debela Tesfaye Gemechu, Michael Zock, Solomon Teferra |
| Abstract | |
| Tasks | Information Retrieval, Question Answering, Text Summarization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-2005/ |
| https://www.aclweb.org/anthology/N16-2005 | |
| PWC | https://paperswithcode.com/paper/combining-syntactic-patterns-and-wikipedias |
| Repo | |
| Framework | |
Natural Language Generation through Character-based RNNs with Finite-state Prior Knowledge
| Title | Natural Language Generation through Character-based RNNs with Finite-state Prior Knowledge |
| Authors | Raghav Goyal, Marc Dymetman, Eric Gaussier |
| Abstract | Recently Wen et al. (2015) have proposed a Recurrent Neural Network (RNN) approach to the generation of utterances from dialog acts, and shown that although their model requires less effort to develop than a rule-based system, it is able to improve certain aspects of the utterances, in particular their naturalness. However their system employs generation at the word-level, which requires one to pre-process the data by substituting named entities with placeholders. This pre-processing prevents the model from handling some contextual effects and from managing multiple occurrences of the same attribute. Our approach uses a character-level model, which unlike the word-level model makes it possible to learn to {``}copy{''} information from the dialog act to the target without having to pre-process the input. In order to avoid generating non-words and inventing information not present in the input, we propose a method for incorporating prior knowledge into the RNN in the form of a weighted finite-state automaton over character sequences. Automatic and human evaluations show improved performance over baselines on several evaluation criteria. | |
| Tasks | Language Modelling, Machine Translation, Named Entity Recognition, Text Generation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1103/ |
| https://www.aclweb.org/anthology/C16-1103 | |
| PWC | https://paperswithcode.com/paper/natural-language-generation-through-character |
| Repo | |
| Framework | |
The Denoised Web Treebank: Evaluating Dependency Parsing under Noisy Input Conditions
| Title | The Denoised Web Treebank: Evaluating Dependency Parsing under Noisy Input Conditions |
| Authors | Joachim Daiber, Rob van der Goot |
| Abstract | We introduce the Denoised Web Treebank: a treebank including a normalization layer and a corresponding evaluation metric for dependency parsing of noisy text, such as Tweets. This benchmark enables the evaluation of parser robustness as well as text normalization methods, including normalization as machine translation and unsupervised lexical normalization, directly on syntactic trees. Experiments show that text normalization together with a combination of domain-specific and generic part-of-speech taggers can lead to a significant improvement in parsing accuracy on this test set. |
| Tasks | Dependency Parsing, Lexical Normalization, Machine Translation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1102/ |
| https://www.aclweb.org/anthology/L16-1102 | |
| PWC | https://paperswithcode.com/paper/the-denoised-web-treebank-evaluating |
| Repo | |
| Framework | |
Evaluation Strategies for Computational Construction Grammars
| Title | Evaluation Strategies for Computational Construction Grammars |
| Authors | T{^a}nia Marques, Katrien Beuls |
| Abstract | Despite the growing number of Computational Construction Grammar implementations, the field is still lacking evaluation methods to compare grammar fragments across different platforms. Moreover, the hand-crafted nature of most grammars requires profiling tools to understand the complex interactions between constructions of different types. This paper presents a number of evaluation measures, partially based on existing measures in the field of semantic parsing, that are especially relevant for reversible grammar formalisms. The measures are tested on a grammar fragment for European Portuguese clitic placement that is currently under development. |
| Tasks | Semantic Parsing |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1108/ |
| https://www.aclweb.org/anthology/C16-1108 | |
| PWC | https://paperswithcode.com/paper/evaluation-strategies-for-computational |
| Repo | |
| Framework | |
Event Embeddings for Semantic Script Modeling
| Title | Event Embeddings for Semantic Script Modeling |
| Authors | Ashutosh Modi |
| Abstract | |
| Tasks | Common Sense Reasoning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-1008/ |
| https://www.aclweb.org/anthology/K16-1008 | |
| PWC | https://paperswithcode.com/paper/event-embeddings-for-semantic-script-modeling |
| Repo | |
| Framework | |
Semantic overfitting: what `world’ do we consider when evaluating disambiguation of text?
| Title | Semantic overfitting: what `world’ do we consider when evaluating disambiguation of text? | |
| Authors | Filip Ilievski, Marten Postma, Piek Vossen |
| Abstract | Semantic text processing faces the challenge of defining the relation between lexical expressions and the world to which they make reference within a period of time. It is unclear whether the current test sets used to evaluate disambiguation tasks are representative for the full complexity considering this time-anchored relation, resulting in semantic overfitting to a specific period and the frequent phenomena within. We conceptualize and formalize a set of metrics which evaluate this complexity of datasets. We provide evidence for their applicability on five different disambiguation tasks. To challenge semantic overfitting of disambiguation systems, we propose a time-based, metric-aware method for developing datasets in a systematic and semi-automated manner, as well as an event-based QA task. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1112/ |
| https://www.aclweb.org/anthology/C16-1112 | |
| PWC | https://paperswithcode.com/paper/semantic-overfitting-what-world-do-we |
| Repo | |
| Framework | |
Learning Linguistic Descriptors of User Roles in Online Communities
| Title | Learning Linguistic Descriptors of User Roles in Online Communities |
| Authors | Alex Wang, William L. Hamilton, Jure Leskovec |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5610/ |
| https://www.aclweb.org/anthology/W16-5610 | |
| PWC | https://paperswithcode.com/paper/learning-linguistic-descriptors-of-user-roles |
| Repo | |
| Framework | |
NLDS-UCSC at SemEval-2016 Task 6: A Semi-Supervised Approach to Detecting Stance in Tweets
| Title | NLDS-UCSC at SemEval-2016 Task 6: A Semi-Supervised Approach to Detecting Stance in Tweets |
| Authors | Amita Misra, Brian Ecker, H, Theodore leman, Nicolas Hahn, Marilyn Walker |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1068/ |
| https://www.aclweb.org/anthology/S16-1068 | |
| PWC | https://paperswithcode.com/paper/nlds-ucsc-at-semeval-2016-task-6-a-semi |
| Repo | |
| Framework | |
Monday mornings are my fave :) #not Exploring the Automatic Recognition of Irony in English tweets
| Title | Monday mornings are my fave :) #not Exploring the Automatic Recognition of Irony in English tweets |
| Authors | Cynthia Van Hee, Els Lefever, V{'e}ronique Hoste |
| Abstract | Recognising and understanding irony is crucial for the improvement natural language processing tasks including sentiment analysis. In this study, we describe the construction of an English Twitter corpus and its annotation for irony based on a newly developed fine-grained annotation scheme. We also explore the feasibility of automatic irony recognition by exploiting a varied set of features including lexical, syntactic, sentiment and semantic (Word2Vec) information. Experiments on a held-out test set show that our irony classifier benefits from this combined information, yielding an F1-score of 67.66{%}. When explicit hashtag information like {#}irony is included in the data, the system even obtains an F1-score of 92.77{%}. A qualitative analysis of the output reveals that recognising irony that results from a polarity clash appears to be (much) more feasible than recognising other forms of ironic utterances (e.g., descriptions of situational irony). |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1257/ |
| https://www.aclweb.org/anthology/C16-1257 | |
| PWC | https://paperswithcode.com/paper/monday-mornings-are-my-fave-not-exploring-the |
| Repo | |
| Framework | |
High Accuracy Rule-based Question Classification using Question Syntax and Semantics
| Title | High Accuracy Rule-based Question Classification using Question Syntax and Semantics |
| Authors | Harish Tayyar Madabushi, Mark Lee |
| Abstract | We present in this paper a purely rule-based system for Question Classification which we divide into two parts: The first is the extraction of relevant words from a question by use of its structure, and the second is the classification of questions based on rules that associate these words to Concepts. We achieve an accuracy of 97.2{%}, close to a 6 point improvement over the previous State of the Art of 91.6{%}. Additionally, we believe that machine learning algorithms can be applied on top of this method to further improve accuracy. |
| Tasks | Feature Selection, Question Answering, Text Classification |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1116/ |
| https://www.aclweb.org/anthology/C16-1116 | |
| PWC | https://paperswithcode.com/paper/high-accuracy-rule-based-question |
| Repo | |
| Framework | |
SemEval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation
| Title | SemEval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation |
| Authors | Eneko Agirre, Carmen Banea, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, Rada Mihalcea, German Rigau, Janyce Wiebe |
| Abstract | |
| Tasks | Machine Translation, Natural Language Inference, Question Answering, Semantic Textual Similarity |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1081/ |
| https://www.aclweb.org/anthology/S16-1081 | |
| PWC | https://paperswithcode.com/paper/semeval-2016-task-1-semantic-textual |
| Repo | |
| Framework | |
DLS@CU at SemEval-2016 Task 1: Supervised Models of Sentence Similarity
| Title | DLS@CU at SemEval-2016 Task 1: Supervised Models of Sentence Similarity |
| Authors | Md Arafat Sultan, Steven Bethard, Tamara Sumner |
| Abstract | |
| Tasks | Machine Translation, Natural Language Inference, Question Answering, Semantic Textual Similarity, Text Summarization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1099/ |
| https://www.aclweb.org/anthology/S16-1099 | |
| PWC | https://paperswithcode.com/paper/dlscu-at-semeval-2016-task-1-supervised |
| Repo | |
| Framework | |
Semantically Motivated Hebrew Verb-Noun Multi-Word Expressions Identification
| Title | Semantically Motivated Hebrew Verb-Noun Multi-Word Expressions Identification |
| Authors | Chaya Liebeskind, Yaakov HaCohen-Kerner |
| Abstract | Identification of Multi-Word Expressions (MWEs) lies at the heart of many natural language processing applications. In this research, we deal with a particular type of Hebrew MWEs, Verb-Noun MWEs (VN-MWEs), which combine a verb and a noun with or without other words. Most prior work on MWEs classification focused on linguistic and statistical information. In this paper, we claim that it is essential to utilize semantic information. To this end, we propose a semantically motivated indicator for classifying VN-MWE and define features that are related to various semantic spaces and combine them as features in a supervised classification framework. We empirically demonstrate that our semantic feature set yields better performance than the common linguistic and statistical feature sets and that combining semantic features contributes to the VN-MWEs identification task. |
| Tasks | Information Retrieval, Machine Translation, Question Answering, Text Generation, Text Summarization, Word Sense Disambiguation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1118/ |
| https://www.aclweb.org/anthology/C16-1118 | |
| PWC | https://paperswithcode.com/paper/semantically-motivated-hebrew-verb-noun-multi |
| Repo | |
| Framework | |
