SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text representation at a feature level as input to a single-stream Transformer, or use a two-stream cross-modal Transformer to align the image-text representation at a high-level semantic space. In real-world image-text data, we observe that it is easy for some of the image-text pairs to align simple semantics on both modalities, while others may be related after higher-level abstraction. Therefore, in this paper, we propose a new pre-training method SemVLP, which jointly aligns both the low-level and high-level semantics between image and text representations. The model is pre-trained iteratively with two prevalent fashions: single-stream pre-training to align at a fine-grained feature level and two-stream pre-training to align high-level semantics, by employing a shared Transformer network with a pluggable cross-modal attention module. An extensive set of experiments have been conducted on four well-established vision-language understanding tasks to demonstrate the effectiveness of the proposed SemVLP in aligning cross-modal representations towards different semantic granularities.

Latent Template Induction with Gumbel-CRFs

Learning to control the structure of sentences is a challenging problem in text generation. Existing work either relies on simple deterministic approaches or RL-based hard structures. We explore the use of structured variational autoencoders to infer latent templates for sentence generation using a soft, continuous relaxation in order to utilize reparameterization for training. Specifically, we propose a Gumbel-CRF, a continuous relaxation of the CRF sampling algorithm using a relaxed Forward-Filtering Backward-Sampling (FFBS) approach. As a reparameterized gradient estimator, the Gumbel-CRF gives more stable gradients than score-function based estimators. As a structured inference network, we show that it learns interpretable templates during training, which allows us to control the decoder during testing. We demonstrate the effectiveness of our methods with experiments on data-to-text generation and unsupervised paraphrase generation.

VECO: Variable Encoder-decoder Pre-training for Cross-lingual Understanding and Generation

Recent studies about learning multilingual representations have achieved significant performance gains across a wide range of downstream cross-lingual tasks. They train either an encoder-only Transformer mainly for understanding tasks, or an encoder-decoder Transformer specifically for generation tasks, ignoring the correlation between the two tasks and frameworks. In contrast, this paper presents a variable encoder-decoder (VECO) pre-training approach to unify the two mainstreams in both model architectures and pre-training tasks. VECO splits the standard Transformer block into several sub-modules trained with both inner-sequence and cross-sequence masked language modeling, and correspondingly reorganizes certain sub-modules for understanding and generation tasks during inference. Such a workflow not only ensures to train the most streamlined parameters necessary for two kinds of tasks, but also enables them to boost each other via sharing common sub-modules. As a result, VECO delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark covering text classification, sequence labeling, question answering, and sentence retrieval. For generation tasks, VECO also outperforms all existing cross-lingual models and state-of-the-art Transformer variants on WMT14 English-to-German and English-to-French translation datasets, with gains of up to 1$\sim$2 BLEU.

PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation

Self-supervised pre-training has emerged as a powerful technique for natural language understanding and generation, such as BERT, MASS and BART. The existing pre-training techniques employ autoencoding and/or autoregressive objectives to train Transformer-based models by recovering original word tokens from corrupted text with some masked tokens. In this work, we present PALM which pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus especially for downstream generation conditioned on context, such as generative question answering and conversational response generation. PALM minimizes the mismatch introduced by the existing denoising scheme between pre-training and fine-tuning where generation is more than reconstructing original text. With a novel pre-training scheme, PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on Gigaword and conversational response generation on Cornell Movie Dialogues.

Symmetric Regularization based BERT for Pair-wise Semantic Reasoning

The ability of semantic reasoning over the sentence pair is essential for many natural language understanding tasks, e.g., natural language inference and machine reading comprehension. A recent significant improvement in these tasks comes from BERT. As reported, the next sentence prediction (NSP) in BERT, which learns the contextual relationship between two sentences, is of great significance for downstream problems with sentence-pair input. Despite the effectiveness of NSP, we suggest that NSP still lacks the essential signal to distinguish between entailment and shallow correlation. To remedy this, we propose to augment the NSP task to a 3-class categorization task, which includes a category for previous sentence prediction (PSP). The involvement of PSP encourages the model to focus on the informative semantics to determine the sentence order, thereby improves the ability of semantic understanding. This simple modification yields remarkable improvement against vanilla BERT. To further incorporate the document-level information, the scope of NSP and PSP is expanded into a broader range, i.e., NSP and PSP also include close but nonsuccessive sentences, the noise of which is mitigated by the label-smoothing technique. Both qualitative and quantitative experimental results demonstrate the effectiveness of the proposed method. Our method consistently improves the performance on the NLI and MRC benchmarks, including the challenging HANS dataset~\cite{hans}, suggesting that the document-level task is still promising for the pre-training.

Incorporating External Knowledge into Machine Reading for Generative Question Answering

Commonsense and background knowledge is required for a QA model to answer many nontrivial questions. Different from existing work on knowledge-aware QA, we focus on a more challenging task of leveraging external knowledge to generate answers in natural language for a given question with context. In this paper, we propose a new neural model, Knowledge-Enriched Answer Generator (KEAG), which is able to compose a natural answer by exploiting and aggregating evidence from all four information sources available: question, passage, vocabulary and knowledge. During the process of answer generation, KEAG adaptively determines when to utilize symbolic knowledge and which fact from the knowledge is useful. This allows the model to exploit external knowledge that is not explicitly stated in the given text, but that is relevant for generating an answer. The empirical study on public benchmark of answer generation demonstrates that KEAG improves answer quality over models without knowledge and existing knowledge-aware models, confirming its effectiveness in leveraging knowledge.

StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding

Recently, the pre-trained language model, BERT, has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as sentiment classification, natural language inference, semantic textual similarity and question answering. Inspired by the linearization exploration work of Elman, we extend BERT to a new model, StructBERT, by incorporating language structures into pre-training. Specifically, we pre-train StructBERT with two auxiliary tasks to make the most of the sequential order of words and sentences, which leverage language structures at the word and sentence levels, respectively. As a result, the new model is adapted to different levels of language understanding required by downstream tasks. The StructBERT with structural pre-training gives surprisingly good empirical results on a variety of downstream tasks, including pushing the state-of-the-art on the GLUE benchmark to 84.5 (with Top 1 achievement on the Leaderboard at the time of paper submission), the F1 score on SQuAD v1.1 question answering to 93.0, the accuracy on SNLI to 91.7.

A Deep Cascade Model for Multi-Document Reading Comprehension

A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC), while efficiency is obtained from improvements in preliminary retrieval components such as candidate document selection and paragraph ranking. Given the complexity of the real-world multi-document MRC scenario, it is difficult to jointly optimize both in an end-to-end system. To address this problem, we develop a novel deep cascade learning model, which progressively evolves from the document-level and paragraph-level ranking of candidate texts to more precise answer extraction with machine reading comprehension. Specifically, irrelevant documents and paragraphs are first filtered out with simple functions for efficiency consideration. Then we jointly train three modules on the remaining texts for better tracking the answer: the document extraction, the paragraph extraction and the answer extraction. Experiment results show that the proposed method outperforms the previous state-of-the-art methods on two large-scale multi-document benchmark datasets, i.e., TriviaQA and DuReader. In addition, our online system can stably serve typical scenarios with millions of daily requests in less than 50ms.

A Neural Comprehensive Ranker (NCR) for Open-Domain Question Answering

This paper proposes a novel neural machine reading model for open-domain question answering at scale. Existing machine comprehension models typically assume that a short piece of relevant text containing answers is already identified and given to the models, from which the models are designed to extract answers. This assumption, however, is not realistic for building a large-scale open-domain question answering system which requires both deep text understanding and identifying relevant text from corpus simultaneously. In this paper, we introduce Neural Comprehensive Ranker (NCR) that integrates both passage ranking and answer extraction in one single framework. A Q&A system based on this framework allows users to issue an open-domain question without needing to provide a piece of text that must contain the answer. Experiments show that the unified NCR model is able to outperform the states-of-the-art in both retrieval of relevant text and answer extraction.

KeyVec: Key-semantics Preserving Document Representations

Previous studies have demonstrated the empirical success of word embeddings in various applications. In this paper, we investigate the problem of learning distributed representations for text documents which many machine learning algorithms take as input for a number of NLP tasks. We propose a neural network model, KeyVec, which learns document representations with the goal of preserving key semantics of the input text. It enables the learned low-dimensional vectors to retain the topics and important information from the documents that will flow to downstream tasks. Our empirical evaluations show the superior quality of KeyVec representations in two different document understanding tasks.