Articles

In this paper we tackle a challenging name tagging problem in an emergent setting - the tagger needs to be complete within a few hours for a new incident language (IL) us- ing very few resources. Inspired by observing how human annotators attack this challenge, we propose a new expectation-driven …...

Word segmentation is usually recognized as the first step for many Chinese natural lan- guage processing tasks, yet its impact on these subsequent tasks is relatively under-studied. For example, how to solve the mismatch prob- lem when applying an existing word seg- menter to new data? Does a better word …...

We present expected F-measure training for shift-reduce parsing with RNNs, which en- ables the learning of a global parsing model optimized for sentence-level F1. We apply the model to CCG parsing, where it improves over a strong greedy RNN baseline, by 1.47% F1, yielding state-of-the-art results for shift- reduce CCG …...

We introduce a novel technique called dynamic feature induction that keeps inducing high di- mensional features automatically until the fea- ture space becomes ‘more’ linearly separable. Dynamic feature induction searches for the fea- ture combinations that give strong clues for distinguishing certain label pairs, and gener- ates joint features from …...

We introduce recurrent neural network gram- mars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Experi- ments show that they provide better parsing in English than any single previously published supervised generative model and better lan- …...

Obtaining common sense knowledge using current information extraction techniques is extremely challenging. In this work, we in- stead propose to derive simple common sense statements from fully annotated object detec- tion corpora such as the Microsoft Common Objects in Context dataset. We show that many thousands of common sense facts …...

We introduce a new task, visual sense disam- biguation for verbs: given an image and a verb, assign the correct sense of the verb, i.e., the one that describes the action depicted in the image. Just as textual word sense disambigua- tion is useful for a wide range of NLP …...

We demonstrate that a state-of-the-art parser can be built using only a lexical tagging model and a deterministic grammar, with no ex- plicit model of bi-lexical dependencies. In- stead, all dependencies are implicitly encoded in an LSTM supertagger that assigns CCG lex- ical categories. The parser significantly out- performs all …...

In this paper we present new state-of-the-art performance on CCG supertagging and pars- ing. Our model outperforms existing ap- proaches by an absolute gain of 1.5%. We an- alyze the performance of several neural mod- els and demonstrate that while feed-forward architectures can compete with bidirectional LSTMs on POS tagging, …...

Recently there has been a lot of interest in learning common representations for multiple views of data. Typically, such common rep- resentations are learned using a parallel cor- pus between the two views (say, 1M images and their English captions). In this work, we address a real-world scenario where no …...

Metaphor is pervasive in our communication, which makes it an important problem for nat- ural language processing (NLP). Numerous approaches to metaphor processing have thus been proposed, all of which relied on linguis- tic features and textual data to construct their models. Human metaphor comprehension is, however, known to rely …...

Semantic Role Labeling (SRL) captures se- mantic roles (or participants) such as agent, patient, and theme associated with verbs from the text. While it provides important in- termediate semantic representations for many traditional NLP tasks (such as information ex- traction and question answering), it does not capture grounded semantics so …...

In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors’ capability for judging semantic similarity. Applying this method to publicly available pre-trained word vectors leads to a new state of the art perfor- mance on …...

Public debates are a common platform for pre- senting and juxtaposing diverging views on important issues. In this work we propose a methodology for tracking how ideas flow be- tween participants throughout a debate. We use this approach in a case study of Oxford- style debates—a competitive format where the …...

We propose a first-ever attempt to employ a Long Short-Term memory based framework to predict humor in dialogues. We analyze data from a popular TV-sitcom, whose canned laughters give an indication of when the au- dience would react. We model the setup- punchline relation of conversational humor with a Long …...

Moving from limited-domain natural lan- guage generation (NLG) to open domain is difficult because the number of semantic in- put combinations grows exponentially with the number of domains. Therefore, it is im- portant to leverage existing resources and ex- ploit similarities between domains to facilitate domain adaptation. In this paper, …...

In this paper we present the first, to the best of our knowledge, discourse parser that is able to predict non-tree DAG structures. We use Integer Linear Programming (ILP) to encode both the objective function and the constraints as global decoding over local scores. Our un- derlying data come from …...

ive Sentence Summarization with Attentive Recurrent Neural Networks Sumit Chopra Facebook AI Research spchopra@fb.com Michael Auli Facebook AI Research michaelauli@fb.com Alexander M. Rush Harvard SEAS srush@seas.harvard.edu Abstract Abstractive Sentence Summarization gener- ates a shorter version of a given sentence while attempting to preserve its meaning. We intro- duce a conditional …...

Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., I don’t know) regardless of the input. We sug- gest that the traditional objective function, i.e., the likelihood of output (response) given input (message) is unsuited to response generation tasks. Instead we propose using …...

A corpus of inference rules between a pair of relation phrases is typically generated us- ing the statistical overlap of argument-pairs associated with the relations (e.g., PATTY, CLEAN). We investigate knowledge-guided linguistic rewrites as a secondary source of ev- idence and find that they can vastly improve the quality of …...