Articles

We propose a cross-lingual framework for learning coreference resolvers for resource-poor target languages, given a re- solver in a source language. Our method uses word-aligned bitext to project infor- mation from the source to the target. To handle task-specific costs, we propose a softmax-margin variant of posterior regu- larization, and …...

We introduce a simple, non-linear mention-ranking model for coreference resolution that attempts to learn distinct feature representations for anaphoricity detection and antecedent ranking, which we encourage by pre-training on a pair of corresponding subtasks. Although we use only simple, unconjoined features, the model is able to learn useful representa- tions, …...

Mention pair models that predict whether or not two mentions are coreferent have historically been very effective for coref- erence resolution, but do not make use of entity-level information. However, we show that the scores produced by such models can be aggregated to define pow- erful entity-level features between clusters …...

Work in grammar induction should help shed light on the amount of syntactic struc- ture that is discoverable from raw word or tag sequences. But since most cur- rent grammar induction algorithms pro- duce unlabeled dependencies, it is diffi- cult to analyze what types of constructions these algorithms can or …...

In this paper, we introduce a new method for the problem of unsupervised depen- dency parsing. Most current approaches are based on generative models. Learning the parameters of such models relies on solving a non-convex optimization prob- lem, thus making them sensitive to initial- ization. We propose a new convex …...

Syntactic annotation is a hard task, but it can be made easier by allowing annotators flexibility to leave aspects of a sentence underspecified. Unfortunately, partial an- notations are not typically directly usable for training parsers. We describe a method for imputing missing dependencies from sentences that have been partially anno- …...

Recursive neural network is one of the most successful deep learning models for natural language processing due to the compositional nature of text. The model recursively composes the vector of a parent phrase from those of child words or phrases, with a key compo- nent named composition function. Al- though …...

In this paper, we introduce Long Short- Term Memory (LSTM) recurrent network for twitter sentiment prediction. With the help of gates and constant error carousels in the memory block structure, the model could handle interactions between words through a flexible compositional function. Experiments on a public noisy labelled data show …...

We propose a novel semantic parsing framework for question answering using a knowledge base. We define a query graph that resembles subgraphs of the knowl- edge base and can be directly mapped to a logical form. Semantic parsing is re- duced to query graph generation, formu- lated as a staged …...

A recent distributional approach to word- analogy problems (Mikolov et al., 2013b) exploits interesting regularities in the structure of the space of representations. Investigating further, we find that per- formance on this task can be related to orthogonality within the space. Explic- itly designing such structure into a neu- ral …...

We consider the problem of building scal- able semantic parsers for Freebase, and present a new approach for learning to do partial analyses that ground as much of the input text as possible without requiring that all content words be mapped to Freebase concepts. We study this problem on two …...

Existing distributed representations are limited in utilizing structured knowledge to improve semantic relatedness modeling. We propose a principled framework of em- bedding entities that integrates hierarchi- cal information from large-scale knowl- edge bases. The novel embedding model associates each category node of the hi- erarchy with a distance metric. To …...

This work develops a new statistical un- derstanding of word embeddings induced from transformed count data. Using the class of hidden Markov models (HMMs) underlying Brown clustering as a genera- tive model, we demonstrate how canoni- cal correlation analysis (CCA) and certain count transformations permit efficient and effective recovery of …...

This paper describes a novel sequence la- beling method for identifying generic ex- pressions, which refer to kinds or arbitrary members of a class, in discourse context. The automatic recognition of such expres- sions is important for any natural language processing task that requires text under- standing. Prior work has …...

How do we build a semantic parser in a new domain starting with zero training ex- amples? We introduce a new methodol- ogy for this setting: First, we use a simple grammar to generate logical forms paired with canonical utterances. The logical forms are meant to cover the desired set …...

There is a growing interest in research- ing null instantiations, which are those implicit semantic arguments. Many of these implicit arguments can be linked to referents in context, and their discoveries are of great benefits to semantic process- ing. We address the issue of automat- ically identifying and resolving implicit …...

This paper proposes a novel approach for incorporating discourse information into machine comprehension applications. Traditionally, such information is com- puted using off-the-shelf discourse analyz- ers. This design provides limited oppor- tunities for guiding the discourse parser based on the requirements of the target task. In contrast, our model induces re- …...

The goal of this research is to build a model to predict stock price movement us- ing sentiments on social media. A new feature which captures topics and their sentiments simultaneously is introduced in the prediction model. In addition, a new topic model TSLDA is proposed to obtain this feature. …...

This paper investigates the problem of cross-lingual dependency parsing, aim- ing at inducing dependency parsers for low-resource languages while using only training data from a resource-rich lan- guage (e.g. English). Existing approaches typically don’t include lexical features, which are not transferable across lan- guages. In this paper, we bridge the …...

Treebanks are key resources for develop- ing accurate statistical parsers. However, building treebanks is expensive and time- consuming for humans. For domains re- quiring deep subject matter expertise such as law and medicine, treebanking is even more difficult. To reduce annotation costs for these domains, we develop methods to improve …...