Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are motivated to distill the rich knowledge embedded inside a well-trained teacher text model to the student speech model. We propose a novel method called the Distilling a Language model to a Speech model (Distill-L2S), which aligns the latent representations of two different modalities. The subtle differences are handled by the shrinking mechanism, nearest-neighbor interpolation, and a learnable linear projection layer. We demonstrate the effectiveness of our distillation method by applying it to the multilingual automatic speech recognition (ASR) task. We distill the transformer-based cross-lingual language model (InfoXLM) while fine-tuning the large-scale multilingual ASR model (XLSR-wav2vec 2.0) for each language. We show the superiority of our method on 20 low-resource languages of the CommonVoice dataset with less than 100 hours of speech data.
This paper proposes an approach that generates multiple 3D human meshes from text. The human shapes are represented by 3D meshes based on the SMPL model. The model's performance is evaluated on the COCO dataset, which contains challenging human shapes and intricate interactions between individuals. The model is able to capture the dynamics of the scene and the interactions between individuals based on text. We further show how using such a shape as input to image synthesis frameworks helps to constrain the network to synthesize humans with realistic human shapes.
Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e.g., BART and T5), have exhibited compelling performance on various natural language generation tasks. However, the black-box nature of these models limits their application in tasks where specific rules (e.g., controllable constraints, prior knowledge) need to be executed. Previous works either design specific model structure (e.g., Copy Mechanism corresponding to the rule "the generated output should include certain words in the source input") or implement specialized inference algorithm (e.g., Constrained Beam Search) to execute particular rules through the text generation. These methods require careful design case-by-case and are difficult to support multiple rules concurrently. In this paper, we propose a novel module named Neural Rule-Execution Tracking Machine that can be equipped into various transformer-based generators to leverage multiple rules simultaneously to guide the neural generation model for superior generation performance in a unified and scalable way. Extensive experimental results on several benchmarks verify the effectiveness of our proposed model in both controllable and general text generation.
Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language model to perform the relation inference and a language model to generate the corresponding explanation. However, the pre-trained vision-language models mainly build token-level alignment between text and image yet ignore the high-level semantic alignment between the phrases (chunks) and visual contents, which is critical for vision-language reasoning. Moreover, the explanation generator based only on the encoded joint representation does not explicitly consider the critical decision-making points of relation inference. Thus the generated explanations are less faithful to visual-language reasoning. To mitigate these problems, we propose a unified Chunk-aware Alignment and Lexical Constraint based method, dubbed as CALeC. It contains a Chunk-aware Semantic Interactor (arr. CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr. LeCG). Specifically, CSI exploits the sentence structure inherent in language and various image regions to build chunk-aware semantic alignment. Relation inferrer uses an attention-based reasoning network to incorporate the token-level and chunk-level vision-language representations. LeCG utilizes lexical constraints to expressly incorporate the words or chunks focused by the relation inferrer into explanation generation, improving the faithfulness and informativeness of the explanations. We conduct extensive experiments on three datasets, and experimental results indicate that CALeC significantly outperforms other competitor models on inference accuracy and quality of generated explanations.
Expert-layman text style transfer technologies have the potential to improve communication between members of scientific communities and the general public. High-quality information produced by experts is often filled with difficult jargon laypeople struggle to understand. This is a particularly notable issue in the medical domain, where layman are often confused by medical text online. At present, two bottlenecks interfere with the goal of building high-quality medical expert-layman style transfer systems: a dearth of pretrained medical-domain language models spanning both expert and layman terminologies and a lack of parallel corpora for training the transfer task itself. To mitigate the first issue, we propose a novel language model (LM) pretraining task, Knowledge Base Assimilation, to synthesize pretraining data from the edges of a graph of expert- and layman-style medical terminology terms into an LM during self-supervised learning. To mitigate the second issue, we build a large-scale parallel corpus in the medical expert-layman domain using a margin-based criterion. Our experiments show that transformer-based models pretrained on knowledge base assimilation and other well-established pretraining tasks fine-tuning on our new parallel corpus leads to considerable improvement against expert-layman transfer benchmarks, gaining an average relative improvement of our human evaluation, the Overall Success Rate (OSR), by 106%.
Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is costly to acquire and difficult to define and annotate accurately. In this paper, we propose a novel framework for learning style representation from abundant plain text in a self-supervised manner. It leverages an emotion lexicon and uses contrastive learning and deep clustering. We further integrate the style representation as a conditioned embedding in a multi-style Transformer TTS. Comparing with multi-style TTS by predicting style tags trained on the same dataset but with human annotations, our method achieves improved results according to subjective evaluations on both in-domain and out-of-domain test sets in audiobook speech. Moreover, with implicit context-aware style representation, the emotion transition of synthesized audio in a long paragraph appears more natural. The audio samples are available on the demo web.
In this paper, we propose a method to identify identical commodities. In e-commerce scenarios, commodities are usually described by both images and text. By definition, identical commodities are those that have identical key attributes and are cognitively identical to consumers. There are two main challenges: 1) The extraction and fusion of multi-modal representation. 2) The ability to verify whether two commodities are identical by comparing the distance between representations with a threshold. To address the above problems, we propose an end-to-end identical commodity verification method based on self-adaptive thresholds. We use a dual-stream network to extract commodity embeddings and threshold embeddings separately and then concatenate them to obtain commodity representation. Our method is able to obtain different thresholds according to different commodities while maintaining the indexability of the entire commodity representation. We experimentally validate the effectiveness of our multimodal feature fusion and the advantages of self-adaptive thresholds. Besides, our method achieves an F1 score of 0.8936 and takes the 3rd place on the leaderboard for the second task of the CCKS-2022 Knowledge Graph Evaluation for Digital Commerce Competition. Code and pretrained models are available at https://github.com/hanchenchen/CCKS2022-track2-solution.
Automatic summary assessment is useful for both machine-generated and human-produced summaries. Automatically evaluating the summary text given the document enables, for example, summary generation system development and detection of inappropriate summaries. Summary assessment can be run in a number of modes: ranking summary generation systems; ranking summaries of a particular document; and estimating the quality of a document-summary pair on an absolute scale. Existing datasets with annotation for summary assessment are usually based on news summarization datasets such as CNN/DailyMail or XSum. In this work, we describe a new dataset, the podcast summary assessment corpus, a collection of podcast summaries that were evaluated by human experts at TREC2020. Compared to existing summary assessment data, this dataset has two unique aspects: (i) long-input, speech podcast based, documents; and (ii) an opportunity to detect inappropriate reference summaries in podcast corpus. First, we examine existing assessment methods, including model-free and model-based methods, and provide benchmark results for this long-input summary assessment dataset. Second, with the aim of filtering reference summary-document pairings for training, we apply summary assessment for data selection. The experimental results on these two aspects provide interesting insights on the summary assessment and generation tasks. The podcast summary assessment data is available.
The performance of sentiment analysis methods has greatly increased in recent years. This is due to the use of various models based on the Transformer architecture, in particular BERT. However, deep neural network models are difficult to train and poorly interpretable. An alternative approach is rule-based methods using sentiment lexicons. They are fast, require no training, and are well interpreted. But recently, due to the widespread use of deep learning, lexicon-based methods have receded into the background. The purpose of the article is to study the performance of the SO-CAL and SentiStrength lexicon-based methods, adapted for the Russian language. We have tested these methods, as well as the RuBERT neural network model, on 16 text corpora and have analyzed their results. RuBERT outperforms both lexicon-based methods on average, but SO-CAL surpasses RuBERT for four corpora out of 16.
Named entity recognition (NER) is the task to detect and classify the entity spans in the text. When entity spans overlap between each other, this problem is named as nested NER. Span-based methods have been widely used to tackle the nested NER. Most of these methods will get a score $n \times n$ matrix, where $n$ means the length of sentence, and each entry corresponds to a span. However, previous work ignores spatial relations in the score matrix. In this paper, we propose using Convolutional Neural Network (CNN) to model these spatial relations in the score matrix. Despite being simple, experiments in three commonly used nested NER datasets show that our model surpasses several recently proposed methods with the same pre-trained encoders. Further analysis shows that using CNN can help the model find nested entities more accurately. Besides, we found that different papers used different sentence tokenizations for the three nested NER datasets, which will influence the comparison. Thus, we release a pre-processing script to facilitate future comparison.