Vision Transformers (ViTs) have been widely used in large-scale Vision and Language Pre-training (VLP) models. Though previous VLP works have proved the effectiveness of ViTs, they still suffer from computational efficiency brought by the long visual sequence. To tackle this problem, in this paper, we propose an efficient vision-and-language pre-training model with Text-Relevant Image Patch Selection, namely TRIPS, which reduces the visual sequence progressively with a text-guided patch-selection layer in the visual backbone for efficient training and inference. The patch-selection layer can dynamically compute text-dependent visual attention to identify the attentive image tokens with text guidance and fuse inattentive ones in an end-to-end manner. Meanwhile, TRIPS does not introduce extra parameters to ViTs. Experimental results on a variety of popular benchmark datasets demonstrate that TRIPS gain a speedup of 40% over previous similar VLP models, yet with competitive or better downstream task performance.
Large-scale pre-trained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. To address both problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross-modal skip-connections.mPLUG is pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. mPLUG also demonstrates strong zero-shot transferability on vision-language and video-language tasks. The code and pre-trained models are available at https://github.com/alibaba/AliceMind
Asymmetric text matching has becoming increasingly indispensable for many downstream tasks (e.g., IR and NLP). Here, asymmetry means that the documents involved for matching hold different amounts of information, e.g., a short query against a relatively longer document. The existing solutions mainly focus on modeling the feature interactions between asymmetric texts, but rarely go one step further to recognize discriminative features and perform feature denoising to enhance relevance learning. In this paper, we propose a novel adaptive feature discrimination and denoising model for asymmetric text matching, called ADDAX. For each asymmetric text pair, ADDAX is devised to explicitly distinguish discriminative features and filter out irrelevant features in a context-aware fashion. Concretely, a matching-adapted gating siamese cell (MAGS) is firstly devised to identify discriminative features and produce the corresponding hybrid representations for a text pair. Afterwards, we introduce a locality-constrained hashing denoiser to perform feature-level denoising by learning a discriminative low-dimensional binary codes for redundantly longer text. Extensive experiments on four real-world datasets from different downstream tasks demostrate that the proposed ADDAX obtains substantial performance gain over 36 up-to-date state-of-the-art alternatives.
Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-stage pipeline. In this paper, we propose the first end-to-end vision-language pre-trained model for both V+L understanding and generation, namely E2E-VLP, where we build a unified Transformer framework to jointly learn visual representation, and semantic alignments between image and text. We incorporate the tasks of object detection and image captioning into pre-training with a unified Transformer encoder-decoder architecture for enhancing visual learning. An extensive set of experiments have been conducted on well-established vision-language downstream tasks to demonstrate the effectiveness of this novel VLP paradigm.
Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important for form image understanding. In this paper, we propose a new pre-training approach, StructuralLM, to jointly leverage cell and layout information from scanned documents. Specifically, we pre-train StructuralLM with two new designs to make the most of the interactions of cell and layout information: 1) each cell as a semantic unit; 2) classification of cell positions. The pre-trained StructuralLM achieves new state-of-the-art results in different types of downstream tasks, including form understanding (from 78.95 to 85.14), document visual question answering (from 72.59 to 83.94) and document image classification (from 94.43 to 96.08).
Recently, question answering (QA) based on machine reading comprehension has become popular. This work focuses on generative QA which aims to generate an abstractive answer to a given question instead of extracting an answer span from a provided passage. Generative QA often suffers from two critical problems: (1) summarizing content irrelevant to a given question, (2) drifting away from a correct answer during generation. In this paper, we address these problems by a novel Rationale-Enriched Answer Generator (REAG), which incorporates an extractive mechanism into a generative model. Specifically, we add an extraction task on the encoder to obtain the rationale for an answer, which is the most relevant piece of text in an input document to a given question. Based on the extracted rationale and original input, the decoder is expected to generate an answer with high confidence. We jointly train REAG on the MS MARCO QA+NLG task and the experimental results show that REAG improves the quality and semantic accuracy of answers over baseline models.
We describe our systems of subtask1 and subtask3 for SemEval-2021 Task 6 on Detection of Persuasion Techniques in Texts and Images. The purpose of subtask1 is to identify propaganda techniques given textual content, and the goal of subtask3 is to detect them given both textual and visual content. For subtask1, we investigate transfer learning based on pre-trained language models (PLMs) such as BERT, RoBERTa to solve data sparsity problems. For subtask3, we extract heterogeneous visual representations (i.e., face features, OCR features, and multimodal representations) and explore various multimodal fusion strategies to combine the textual and visual representations. The official evaluation shows our ensemble model ranks 1st for subtask1 and 2nd for subtask3.
Chinese and Japanese share many characters with similar surface morphology. To better utilize the shared knowledge across the languages, we propose UnihanLM, a self-supervised Chinese-Japanese pretrained masked language model (MLM) with a novel two-stage coarse-to-fine training approach. We exploit Unihan, a ready-made database constructed by linguistic experts to first merge morphologically similar characters into clusters. The resulting clusters are used to replace the original characters in sentences for the coarse-grained pretraining of the MLM. Then, we restore the clusters back to the original characters in sentences for the fine-grained pretraining to learn the representation of the specific characters. We conduct extensive experiments on a variety of Chinese and Japanese NLP benchmarks, showing that our proposed UnihanLM is effective on both mono- and cross-lingual Chinese and Japanese tasks, shedding light on a new path to exploit the homology of languages.
Conditional Text Generation has drawn much attention as a topic of Natural Language Generation (NLG) which provides the possibility for humans to control the properties of generated contents. Current conditional generation models cannot handle emerging conditions due to their joint end-to-end learning fashion. When a new condition added, these techniques require full retraining. In this paper, we present a new framework named Pre-train and Plug-in Variational Auto-Encoder (PPVAE) towards flexible conditional text generation. PPVAE decouples the text generation module from the condition representation module to allow “one-to-many” conditional generation. When a fresh condition emerges, only a lightweight network needs to be trained and works as a plug-in for PPVAE, which is efficient and desirable for real-world applications. Extensive experiments demonstrate the superiority of PPVAE against the existing alternatives with better conditionality and diversity but less training effort.
Recently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing. However, there is currently no cross-task dataset in NLP, which hinders the development of multi-task learning. We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization. MATINF contains 1.07 million question-answer pairs with human-labeled categories and user-generated question descriptions. Based on such rich information, MATINF is applicable for three major NLP tasks, including classification, question answering, and summarization. We benchmark existing methods and a novel multi-task baseline over MATINF to inspire further research. Our comprehensive comparison and experiments over MATINF and other datasets demonstrate the merits held by MATINF.
Aspect-based sentiment classification is a popular task aimed at identifying the corresponding emotion of a specific aspect. One sentence may contain various sentiments for different aspects. Many sophisticated methods such as attention mechanism and Convolutional Neural Networks (CNN) have been widely employed for handling this challenge. Recently, semantic dependency tree implemented by Graph Convolutional Networks (GCN) is introduced to describe the inner connection between aspects and the associated emotion words. But the improvement is limited due to the noise and instability of dependency trees. To this end, we propose a dependency graph enhanced dual-transformer network (named DGEDT) by jointly considering the flat representations learnt from Transformer and graph-based representations learnt from the corresponding dependency graph in an iterative interaction manner. Specifically, a dual-transformer structure is devised in DGEDT to support mutual reinforcement between the flat representation learning and graph-based representation learning. The idea is to allow the dependency graph to guide the representation learning of the transformer encoder and vice versa. The results on five datasets demonstrate that the proposed DGEDT outperforms all state-of-the-art alternatives with a large margin.
Self-supervised pre-training, such as BERT, MASS and BART, has emerged as a powerful technique for natural language understanding and generation. 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. The training goals of existing techniques are often inconsistent with the goals of many language generation tasks, such as generative question answering and conversational response generation, for producing new text given context. This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus, specifically designed for generating new text conditioned on context. The new scheme alleviates the mismatch introduced by the existing denoising scheme between pre-training and fine-tuning where generation is more than reconstructing original text. An extensive set of experiments show that 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 CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
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.
How to generate relevant and informative responses is one of the core topics in response generation area. Following the task formulation of machine translation, previous works mainly consider response generation task as a mapping from a source sentence to a target sentence. To realize this mapping, existing works tend to design intuitive but complex models. However, the relevant information existed in large dialogue corpus is mainly overlooked. In this paper, we propose Sequence to Sequence with Prototype Memory Network (S2SPMN) to exploit the relevant information provided by the large dialogue corpus to enhance response generation. Specifically, we devise two simple approaches in S2SPMN to select the relevant information (named prototypes) from the dialogue corpus. These prototypes are then saved into prototype memory network (PMN). Furthermore, a hierarchical attention mechanism is devised to extract the semantic information from the PMN to assist the response generation process. Empirical studies reveal the advantage of our model over several classical and strong baselines.
Neural network models, based on the attentional encoder-decoder model, have good capability in abstractive text summarization. However, these models are hard to be controlled in the process of generation, which leads to a lack of key information. We propose a guiding generation model that combines the extractive method and the abstractive method. Firstly, we obtain keywords from the text by a extractive model. Then, we introduce a Key Information Guide Network (KIGN), which encodes the keywords to the key information representation, to guide the process of generation. In addition, we use a prediction-guide mechanism, which can obtain the long-term value for future decoding, to further guide the summary generation. We evaluate our model on the CNN/Daily Mail dataset. The experimental results show that our model leads to significant improvements.
In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand. As a fundamental task, information filtering therefore becomes a critical necessity. In this paper, we propose a novel deep relevance model for zero-shot document filtering, named DAZER. DAZER estimates the relevance between a document and a category by taking a small set of seed words relevant to the category. With pre-trained word embeddings from a large external corpus, DAZER is devised to extract the relevance signals by modeling the hidden feature interactions in the word embedding space. The relevance signals are extracted through a gated convolutional process. The gate mechanism controls which convolution filters output the relevance signals in a category dependent manner. Experiments on two document collections of two different tasks (i.e., topic categorization and sentiment analysis) demonstrate that DAZER significantly outperforms the existing alternative solutions, including the state-of-the-art deep relevance ranking models.