Articles

Traditional models of distributional se- mantics suffer from computational issues such as data sparsity for individual lex- emes and complexities of modeling se- mantic composition when dealing with structures larger than single lexical items. In this work, we present a frequency- driven paradigm for robust distributional semantics in terms of …...

We introduce the problem of generation in distributional semantics: Given a distri- butional vector representing some mean- ing, how can we generate the phrase that best expresses that meaning? We mo- tivate this novel challenge on theoretical and practical grounds and propose a sim- ple data-driven approach to the estimation …...

Although the distributional hypothesis has been applied successfully in many natural language processing tasks, systems using distributional information have been lim- ited to a single domain because the dis- tribution of a word can vary between do- mains as the word’s predominant mean- ing changes. However, if it were pos- …...

An important search task in the biomedical domain is to find medical records of pa- tients who are qualified for a clinical trial. One commonly used approach is to apply NLP tools to map terms from queries and documents to concepts and then compute the relevance scores based on the …...

Accurately segmenting a citation string into fields for authors, titles, etc. is a chal- lenging task because the output typically obeys various global constraints. Previous work has shown that modeling soft con- straints, where the model is encouraged, but not require to obey the constraints, can substantially improve segmentation per- …...

Active learning (AL) has been proven ef- fective to reduce human annotation ef- forts in NLP. However, previous studies on AL are limited to applications in a single language. This paper proposes a bilingual active learning paradigm for re- lation classification, where the unlabeled instances are first jointly chosen in …...

Chinese is an ancient hieroglyphic. It is inat- tentive to structure. Therefore, segmenting and parsing Chinese are more difficult and less accurate. In this paper, we propose an Omni- word feature and a soft constraint method for Chinese relation extraction. The Omni-word feature uses every potential word in a sentence …...

A vast majority of L1 vocabulary acqui- sition occurs through incidental learning during reading (Nation, 2001; Schmitt et al., 2001). We propose a probabilistic ap- proach to generating code-mixed text as an L2 technique for increasing retention in adult lexical learning through reading. Our model that takes as input a …...

We study the problem of generating an En- glish sentence given an underlying prob- abilistic grammar, a world and a com- municative goal. We model the genera- tion problem as a Markov decision process with a suitably defined reward function that reflects the communicative goal. We then use probabilistic planning …...

The sentiment captured in opinionated text provides interesting and valuable informa- tion for social media services. However, due to the complexity and diversity of linguistic representations, it is challeng- ing to build a framework that accurately extracts such sentiment. We propose a semi-supervised framework for generat- ing a domain-specific sentiment …...

Automatic extraction of new words is an indispensable precursor to many NLP tasks such as Chinese word segmentation, named entity extraction, and sentimen- t analysis. This paper aims at extract- ing new sentiment words from large-scale user-generated content. We propose a ful- ly unsupervised, purely data-driven frame- work for this …...

Negative expressions are common in natural language text and play a critical role in in- formation extraction. However, the perfor- mances of current systems are far from satis- faction, largely due to its focus on intra- sentence information and its failure to con- sider inter-sentence information. In this paper, we …...

Text-level discourse parsing remains a challenge. The current state-of-the-art overall accuracy in relation assignment is 55.73%, achieved by Joty et al. (2013). However, their model has a high order of time complexity, and thus cannot be ap- plied in practice. In this work, we develop a much faster model whose …...

We use single-agent and multi-agent Rein- forcement Learning (RL) for learning dia- logue policies in a resource allocation ne- gotiation scenario. Two agents learn con- currently by interacting with each other without any need for simulated users (SUs) to train against or corpora to learn from. In particular, we compare …...

Vector space models (VSMs) represent word meanings as points in a high dimen- sional space. VSMs are typically created using a large text corpora, and so repre- sent word semantics as observed in text. We present a new algorithm (JNNSE) that can incorporate a measure of semantics not previously used …...

This paper proposes a simple yet effective framework for semi-supervised dependency parsing at entire tree level, referred to as ambiguity-aware ensemble training. Instead of only using 1- best parse trees in previous work, our core idea is to utilize parse forest (ambiguous labelings) to combine multiple 1-best parse trees generated …...

Lexical resource alignment has been an active field of research over the last decade. However, prior methods for align- ing lexical resources have been either spe- cific to a particular pair of resources, or heavily dependent on the availability of hand-crafted alignment data for the pair of resources to be …...

This paper is concerned with building linguistic re- sources and statistical parsers for deep grammatical relation (GR) analysis of Chinese texts. A set of linguistic rules is defined to explore implicit phrase structural information and thus build high-quality GR annotations that are represented as general di- rected dependency graphs. The …...

We present a hybrid approach to sentence simplification which combines deep se- mantics and monolingual machine transla- tion to derive simple sentences from com- plex ones. The approach differs from pre- vious work in two main ways. First, it is semantic based in that it takes as in- put a …...

Using distributional analysis methods to compute semantic proximity links be- tween words has become commonplace in NLP. The resulting relations are often noisy or difficult to interpret in general. This paper focuses on the issues of eval- uating a distributional resource and filter- ing the relations it contains, but instead …...