Related papers: Transformer-GCRF: Recovering Chinese Dropped Prono…
Pronouns are often dropped in Chinese sentences, and this happens more frequently in conversational genres as their referents can be easily understood from context. Recovering dropped pronouns is essential to applications such as…
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. Recently, Wang et al. (2018) proposed a novel reconstruction-based…
Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recovery. In this paper, we propose a neural recovery machine…
In this paper, we present a neural model for joint dropped pronoun recovery (DPR) and conversational discourse parsing (CDP) in Chinese conversational speech. We show that DPR and CDP are closely related, and a joint model benefits both…
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. To date, very little attention has been paid to the dropped pronoun…
Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semi-supervised approach to…
Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. CRF models the conditional probability of the…
Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…
Distantly supervised relation extraction is widely used to extract relational facts from text, but suffers from noisy labels. Current relation extraction methods try to alleviate the noise by multi-instance learning and by providing…
Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and…
A major challenge in structured prediction is to represent the interdependencies within output structures. When outputs are structured as sequences, linear-chain conditional random fields (CRFs) are a widely used model class which can learn…
The dominant language models (LMs) such as n-gram and neural network (NN) models represent sentence probabilities in terms of conditionals. In contrast, a new trans-dimensional random field (TRF) LM has been recently introduced to show…
Story generation aims to generate a long narrative conditioned on a given input. In spite of the success of prior works with the application of pre-trained models, current neural models for Chinese stories still struggle to generate…
In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntactic and…
We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model. In experiments based on a small number of labeled examples (~1.7K-5K sentences) we evaluate its performance…
In recent years, neural networks have proven to be effective in Chinese word segmentation. However, this promising performance relies on large-scale training data. Neural networks with conventional architectures cannot achieve the desired…
Despite successful applications across a broad range of NLP tasks, conditional random fields ("CRFs"), in particular the linear-chain variant, are only able to model local features. While this has important benefits in terms of inference…
In this paper, we present an approach to improve the accuracy of a strong transition-based dependency parser by exploiting dependency language models that are extracted from a large parsed corpus. We integrated a small number of features…
Deep neural network models for Chinese zero pronoun resolution learn semantic information for zero pronoun and candidate antecedents, but tend to be short-sighted---they often make local decisions. They typically predict coreference chains…
Recognition of handwritten words continues to be an important problem in document analysis and recognition. Existing approaches extract hand-engineered features from word images--which can perform poorly with new data sets. Recently, deep…