Share This Author
Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources
Investigation of unsupervised techniques for acquiring monolingual sentence-level paraphrases from a corpus of temporally and topically clustered news articles collected from thousands of web-based news sources shows that edit distance data is cleaner and more easily-aligned than the heuristic data.
Cross-Sentence N-ary Relation Extraction with Graph LSTMs
- Nanyun Peng, Hoifung Poon, Chris Quirk, Kristina Toutanova, Wen-tau Yih
- Computer ScienceTACL
- 5 April 2017
A general relation extraction framework based on graph long short-term memory networks (graph LSTMs) that can be easily extended to cross-sentence n-ary relation extraction is explored, demonstrating its effectiveness with both conventional supervised learning and distant supervision.
Dependency Treelet Translation: Syntactically Informed Phrasal SMT
An efficient decoder is described and it is shown that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.
Monolingual Machine Translation for Paraphrase Generation
Human evaluation shows that this SMT system outperforms baseline paraphrase generation techniques and, in a departure from previous work, offers better coverage and scalability than the current best-of-breed paraphrasing approaches.
Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment
This work advances the state of the art in parallel sentence extraction by modeling the document level alignment, motivated by the observation that parallel sentence pairs are often found in close proximity.
Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes
This work presents an approach that learns to map natural-language descriptions of simple “if-then” rules to executable code by training and testing on a large corpus of naturally-occurring programs and their natural language descriptions.
deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
In tasks involving generation of conversational responses, ∆BLEU correlates reasonably with human judgments and outperforms sentence-level and IBM BLEU in terms of both Spearman's ρ and Kendall’s τ.
Joint Language and Translation Modeling with Recurrent Neural Networks
This work presents a joint language and translation model based on a recurrent neural network which predicts target words based on an unbounded history of both source and target words which shows competitive accuracy compared to the traditional channel model features.
Novel positional encodings to enable tree-based transformers
This work abstracts the transformer's sinusoidal positional encodings, allowing it to instead use a novel positional encoding scheme to represent node positions within trees, achieving superior performance over both sequence-to-sequence transformers and state-of-the-art tree-based LSTMs on several datasets.
Distant Supervision for Relation Extraction beyond the Sentence Boundary
This paper proposes the first approach for applying distant supervision to cross-sentence relation extraction with a graph representation that can incorporate both standard dependencies and discourse relations, thus providing a unifying way to model relations within and across sentences.