Spain

Sentence matching aims to identify the special relationship between two sentences, and plays a key role in many natural language processing tasks. However, previous studies mainly focused on exploiting either syntactic or semantic information for sentence matching, and no studies consider integrating both of them. In this study, we propose integrating syntax and semantics into BERT with sentence matching. In particular, we use an implicit syntax and semantics integration method that is less sensitive to the output structure information. Thus the implicit integration can alleviate the error propagation problem. The experimental results show that our approach has achieved state-of-the-art or competitive performance on several sentence matching datasets, demonstrating the benefits of implicitly integrating syntactic and semantic features in sentence matching.


COLING 2020

Sentence Matching with Syntax- and Semantics-Aware BERT

pre-training language models

structural information

sentence matching

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

poster

We perform a corpus analysis to develop a representation of the knowledge and reasoning used to interpret indirect speech acts. An indirect speech act (ISA) is an utterance whose intended meaning is different from its literal meaning. We focus on those speech acts in which slight changes in situational or contextual information can switch the dominant intended meaning of an utterance from direct to indirect or vice-versa. We computationalize how various contextual features can influence a speaker’s beliefs, and how these beliefs can influence the intended meaning and choice of the surface form of an utterance. We axiomatize the domain-general patterns of reasoning involved, and implement a proof-of-concept architecture using Answer Set Programming. Our model is presented as a contribution to cognitive science and psycholinguistics, so representational decisions are justified by existing theoretical work.

Reasoning Requirements for Indirect Speech Acts

We reduce the model size of pre-trained word embeddings by a factor of $200$ while preserving its quality. Previous studies in this direction created a smaller word embedding model by reconstructing pre-trained word representations from those of subwords, which allows to store only a smaller number of subword embeddings in the memory. However, previous studies that train the reconstruction models using only target words cannot reduce the model size extremely while preserving its quality. Inspired by the observation of words with similar meanings having similar embeddings, our reconstruction training learns the global relationships among words, which can be employed in various models for word embedding reconstruction. Experimental results on word similarity benchmarks show that the proposed method improves the performance of the all subword-based reconstruction models.

Tiny Word Embeddings Using Globally Informed Reconstruction

Complex question answering (CQA) over raw text is a challenging task. A prominent approach to this task is based on the programmer-interpreter framework, where the programmer maps the question into a sequence of reasoning actions and the interpreter then executes these actions on the raw text. Learning an effective CQA model requires large amounts of human-annotated data, consisting of the ground-truth sequence of reasoning actions, which is time-consuming and expensive to collect at scale. In this paper, we address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machinegenerated questions which are more convenient to parse. We firstly generate synthetic (question, action sequence) pairs by a data generator, and train a semantic parser that associates synthetic questions with their corresponding action sequences. To capture the diversity when applied to natural questions, we learn a projection model to map natural questions into their most similar unnatural questions for which the parser can work well. Without any natural training data, our projection model provides high-quality action sequences for the CQA task. Experimental results show that the QA model trained exclusively with synthetic data outperforms its state-of-the-art counterpart trained on human-labeled data.

Understanding Unnatural Questions Improves Reasoning over Text

This paper studies the problem of generating a summary for a given sentence-image pair. Existing multimodal sequence-to-sequence approaches mainly focus on enhancing the decoder by visual signals, while ignoring that the image can improve the ability of the encoder to identify highlights of a news event or a document. Thus, we propose a multimodal selective gate network that considers reciprocal relationships between textual and multi-level visual features, including global image descriptor, activation grids, and object proposals, to select highlights of the event when encoding the source sentence. In addition, we introduce a modality regularization to encourage the summary to capture the highlights embedded in the image more accurately. To verify the generalization of our model, we adopt the multimodal selective gate to the text-based decoder and multimodal-based decoder. Experimental results on a public multimodal sentence summarization dataset demonstrate the advantage of our models over baselines. Further analysis suggests that our proposed multimodal selective gate network can effectively select important information in the input sentence.

Multimodal Sentence Summarization via Multimodal Selective Encoding

Pre-trained language models provide the foundations for state-of-the-art performance across a wide range of natural language processing tasks, including text classification. However, most classification datasets assume a large amount labeled data, which is commonly not the case in practical settings. In particular, in this paper we compare the performance of a light-weight linear classifier based on word embeddings, i.e., fastText (Joulin et al., 2017), versus a pre-trained language model, i.e., BERT (Devlin et al., 2019), across a wide range of datasets and classification tasks. In general, results show the importance of domain-specific unlabeled data, both in the form of word embeddings or language models. As for the comparison, BERT outperforms all baselines in standard datasets with large training sets. However, in settings with small training datasets a simple method like fastText coupled with domain-specific word embeddings performs equally well or better than BERT, even when pre-trained on domain-specific data.

Go Simple and Pre-Train on Domain-Specific Corpora: On the Role of Training Data for Text Classification

We propose a lattice transformer encoder for Chinese NER by introducing lattice-aware self-attention, which borrows the idea from the relative positional embedding to make self-attention aware of the relative position information in lattice structure.

Porous Lattice Transformer Encoder for Chinese NER

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token with a special token instead of setting zero to words. We further introduce two self-supervised objectives: Replaced Token Detection and Dropped Token Prediction. Our method aims to force model generating target translation with less information, in this way the model can learn textual representation better. Experiments on Chinese-English and English-Romanian benchmark demonstrate the effectiveness of our approach and our model achieves significant improvements over a strong Transformer baseline.

Token Drop mechanism for Neural Machine Translation

Dependency trees have been shown to be effective in capturing long-range relations between target entities. Nevertheless, how to selectively emphasize target-relevant information and remove irrelevant content from the tree is still an open problem.
Existing approaches employing pre-defined rules to eliminate noise may not always yield optimal results due to the complexity and variability of natural language. In this poster, we present a novel architecture named Dynamically Pruned Graph Convolutional Network (DP-GCN), which learns to prune the dependency tree with rethinking in an end-to-end scheme. In each layer of DP-GCN, we employ a selection module to concentrate on nodes expressing the target relation by a set of binary gates and then augment the pruned tree with a pruned semantic graph to ensure the connectivity. After that, we introduce a rethinking mechanism to guide and refine the pruning operation by feeding back the high-level learned features repeatedly. Extensive experimental results demonstrate that our model achieves impressive performance compared to strong competitors.

Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction

This paper addresses the question as to what degree a BERT-based multilingual Spoken Language Understanding (SLU) model can transfer knowledge across languages. Through experiments we will show that, although it works substantially well even on distant language groups, there is still a gap to the ideal multilingual performance. In addition, we propose a novel BERT-based adversarial model architecture to learn language-shared and language-specific representations for
multilingual SLU. Our experimental results prove that the proposed model is capable of narrowing the gap to the ideal multilingual performance.

To What Degree Can Language Borders Be Blurred
In BERT-based Multilingual Spoken Language Understanding?


Skip connection is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through the neural network layers. However, from another point of view, it can also be seen as a modulating mechanism between the input and the output, with the input scaled by a pre-defined value one. In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious gradient exploding or vanishing in line with the deepness of the models, which could by addressed by normalization, in particular, layer normalization, which induces consistent improvements over the plain skip connection. Inspired by the findings, we further propose to adaptively adjust the scale of the input by recursively applying skip connection with layer normalization, which promotes the performance substantially and generalizes well across diverse tasks including both machine translation and image classification datasets.

Sentence Matching with Syntax- and Semantics-Aware BERT

Downloads

Next from COLING 2020

Reasoning Requirements for Indirect Speech Acts

Similar lecture

Pre-trained Language Model Based Active Learning for Sentence Matching

Sentence Matching with Syntax- and Semantics-Aware BERT

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Reasoning Requirements for Indirect Speech Acts

Similar lecture

Pre-trained Language Model Based Active Learning for Sentence Matching

Downloads