Paper Group NANR 90
Is ``Universal Syntax’’ Universally Useful for Learning Distributed Word Representations?. Learning to refine text based recommendations. What Makes Objects Similar: A Unified Multi-Metric Learning Approach. Exploiting Sentence Similarities for Better Alignments. Tense Manages to Predict Implicative Behavior in Verbs. Why Neural Translations are th …
Is ``Universal Syntax’’ Universally Useful for Learning Distributed Word Representations?
| Title | Is ``Universal Syntax’’ Universally Useful for Learning Distributed Word Representations? | |
| Authors | Ivan Vuli{'c}, Anna Korhonen |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2084/ |
| https://www.aclweb.org/anthology/P16-2084 | |
| PWC | https://paperswithcode.com/paper/is-universal-syntax-universally-useful-for |
| Repo | |
| Framework | |
Learning to refine text based recommendations
| Title | Learning to refine text based recommendations |
| Authors | Youyang Gu, Tao Lei, Regina Barzilay, Tommi Jaakkola |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1227/ |
| https://www.aclweb.org/anthology/D16-1227 | |
| PWC | https://paperswithcode.com/paper/learning-to-refine-text-based-recommendations |
| Repo | |
| Framework | |
What Makes Objects Similar: A Unified Multi-Metric Learning Approach
| Title | What Makes Objects Similar: A Unified Multi-Metric Learning Approach |
| Authors | Han-Jia Ye, De-Chuan Zhan, Xue-Min Si, Yuan Jiang, Zhi-Hua Zhou |
| Abstract | Linkages are essentially determined by similarity measures that may be derived from multiple perspectives. For example, spatial linkages are usually generated based on localities of heterogeneous data, whereas semantic linkages can come from various properties, such as different physical meanings behind social relations. Many existing metric learning models focus on spatial linkages, but leave the rich semantic factors unconsidered. Similarities based on these models are usually overdetermined on linkages. We propose a Unified Multi-Metric Learning (UM2L) framework to exploit multiple types of metrics. In UM2L, a type of combination operator is introduced for distance characterization from multiple perspectives, and thus can introduce flexibilities for representing and utilizing both spatial and semantic linkages. Besides, we propose a uniform solver for UM2L which is guaranteed to converge. Extensive experiments on diverse applications exhibit the superior classification performance and comprehensibility of UM2L. Visualization results also validate its ability on physical meanings discovery. |
| Tasks | Metric Learning |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6192-what-makes-objects-similar-a-unified-multi-metric-learning-approach |
| http://papers.nips.cc/paper/6192-what-makes-objects-similar-a-unified-multi-metric-learning-approach.pdf | |
| PWC | https://paperswithcode.com/paper/what-makes-objects-similar-a-unified-multi |
| Repo | |
| Framework | |
Exploiting Sentence Similarities for Better Alignments
| Title | Exploiting Sentence Similarities for Better Alignments |
| Authors | Tao Li, Vivek Srikumar |
| Abstract | |
| Tasks | Natural Language Inference, Paraphrase Identification, Semantic Textual Similarity |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1237/ |
| https://www.aclweb.org/anthology/D16-1237 | |
| PWC | https://paperswithcode.com/paper/exploiting-sentence-similarities-for-better |
| Repo | |
| Framework | |
Tense Manages to Predict Implicative Behavior in Verbs
| Title | Tense Manages to Predict Implicative Behavior in Verbs |
| Authors | Ellie Pavlick, Chris Callison-Burch |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1240/ |
| https://www.aclweb.org/anthology/D16-1240 | |
| PWC | https://paperswithcode.com/paper/tense-manages-to-predict-implicative-behavior |
| Repo | |
| Framework | |
Why Neural Translations are the Right Length
| Title | Why Neural Translations are the Right Length |
| Authors | Xing Shi, Kevin Knight, Deniz Yuret |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1248/ |
| https://www.aclweb.org/anthology/D16-1248 | |
| PWC | https://paperswithcode.com/paper/why-neural-translations-are-the-right-length |
| Repo | |
| Framework | |
Bilingually-constrained Synthetic Data for Implicit Discourse Relation Recognition
| Title | Bilingually-constrained Synthetic Data for Implicit Discourse Relation Recognition |
| Authors | Changxing Wu, Xiaodong Shi, Yidong Chen, Yanzhou Huang, Jinsong Su |
| Abstract | |
| Tasks | Domain Adaptation, Machine Translation, Multi-Task Learning, Question Answering |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1253/ |
| https://www.aclweb.org/anthology/D16-1253 | |
| PWC | https://paperswithcode.com/paper/bilingually-constrained-synthetic-data-for |
| Repo | |
| Framework | |
Encoding Temporal Information for Time-Aware Link Prediction
| Title | Encoding Temporal Information for Time-Aware Link Prediction |
| Authors | Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui |
| Abstract | |
| Tasks | Link Prediction |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1260/ |
| https://www.aclweb.org/anthology/D16-1260 | |
| PWC | https://paperswithcode.com/paper/encoding-temporal-information-for-time-aware |
| Repo | |
| Framework | |
Round Up The Usual Suspects: Knowledge-Based Metaphor Generation
| Title | Round Up The Usual Suspects: Knowledge-Based Metaphor Generation |
| Authors | Tony Veale |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1105/ |
| https://www.aclweb.org/anthology/W16-1105 | |
| PWC | https://paperswithcode.com/paper/round-up-the-usual-suspects-knowledge-based |
| Repo | |
| Framework | |
Multi-Modal Representations for Improved Bilingual Lexicon Learning
| Title | Multi-Modal Representations for Improved Bilingual Lexicon Learning |
| Authors | Ivan Vuli{'c}, Douwe Kiela, Stephen Clark, Marie-Francine Moens |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2031/ |
| https://www.aclweb.org/anthology/P16-2031 | |
| PWC | https://paperswithcode.com/paper/multi-modal-representations-for-improved |
| Repo | |
| Framework | |
The aNALoGuE Challenge: Non Aligned Language GEneration
| Title | The aNALoGuE Challenge: Non Aligned Language GEneration |
| Authors | Jekaterina Novikova, Verena Rieser |
| Abstract | |
| Tasks | Machine Translation, Semantic Parsing, Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6627/ |
| https://www.aclweb.org/anthology/W16-6627 | |
| PWC | https://paperswithcode.com/paper/the-analogue-challenge-non-aligned-language |
| Repo | |
| Framework | |
Cross Sentence Inference for Process Knowledge
| Title | Cross Sentence Inference for Process Knowledge |
| Authors | Samuel Louvan, Chetan Naik, Sadhana Kumaravel, Heeyoung Kwon, Niranjan Balasubramanian, Peter Clark |
| Abstract | |
| Tasks | Semantic Role Labeling |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1151/ |
| https://www.aclweb.org/anthology/D16-1151 | |
| PWC | https://paperswithcode.com/paper/cross-sentence-inference-for-process |
| Repo | |
| Framework | |
From Entity Linking to Question Answering – Recent Progress on Semantic Grounding Tasks
| Title | From Entity Linking to Question Answering – Recent Progress on Semantic Grounding Tasks |
| Authors | Ming-Wei Chang |
| Abstract | Entity linking and semantic parsing have been shown to be crucial to important applications such as question answering and document understanding. These tasks often require structured learning models, which make predictions on multiple interdependent variables. In this talk, I argue that carefully designed structured learning algorithms play a central role in entity linking and semantic parsing tasks. In particular, I will present several new structured learning models for entity linking, which jointly detect mentions and disambiguate entities as well as capture non-textual information. I will then show how to use a staged search procedure to building a state-of-the-art knowledge base question answering system. Finally, if time permits, I will discuss different supervision protocols for training semantic parsers and the value of labeling semantic parses. |
| Tasks | Entity Linking, Knowledge Base Question Answering, Question Answering, Semantic Parsing |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-3902/ |
| https://www.aclweb.org/anthology/W16-3902 | |
| PWC | https://paperswithcode.com/paper/from-entity-linking-to-question-answering-a |
| Repo | |
| Framework | |
QAF: Frame Semantics-based Question Interpretation
| Title | QAF: Frame Semantics-based Question Interpretation |
| Authors | Younggyun Hahm, Sangha Nam, Key-Sun Choi |
| Abstract | Natural language questions are interpreted to a sequence of patterns to be matched with instances of patterns in a knowledge base (KB) for answering. A natural language (NL) question answering (QA) system utilizes meaningful patterns matching the syntac-tic/lexical features between the NL questions and KB. In the most of KBs, there are only binary relations in triple form to represent relation between two entities or entity and a value using the domain specific ontology. However, the binary relation representation is not enough to cover complex information in questions, and the ontology vocabulary sometimes does not cover the lexical meaning in questions. Complex meaning needs a knowledge representation to link the binary relation-type triples in KB. In this paper, we propose a frame semantics-based semantic parsing approach as KB-independent question pre-processing. We will propose requirements of question interpretation in the KBQA perspective, and a query form representation based on our proposed format QAF (Ques-tion Answering with the Frame Semantics), which is supposed to cover the requirements. In QAF, frame semantics roles as a model to represent complex information in questions and to disambiguate the lexical meaning in questions to match with the ontology vocabu-lary. Our system takes a question as an input and outputs QAF-query by the process which assigns semantic information in the question to its corresponding frame semantic structure using the semantic parsing rules. |
| Tasks | Knowledge Base Question Answering, Question Answering, Reading Comprehension, Semantic Parsing |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4412/ |
| https://www.aclweb.org/anthology/W16-4412 | |
| PWC | https://paperswithcode.com/paper/qaf-frame-semantics-based-question |
| Repo | |
| Framework | |
Use of Features for Accentuation of gha~nanta Words
| Title | Use of Features for Accentuation of gha~nanta Words |
| Authors | Samir Janardan Sohoni, Malhar A. Kulkarni |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6329/ |
| https://www.aclweb.org/anthology/W16-6329 | |
| PWC | https://paperswithcode.com/paper/use-of-features-for-accentuation-of-ghaaanta |
| Repo | |
| Framework | |
