With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers. The unsupervised pre-training method based on transformer structure combined with fine-tuning of downstream tasks has achiev
ed great success in the field of text summarization. However, the semantic structure and style of meeting transcripts are quite different from that of articles. In this work, we propose a hierarchical transformer encoder-decoder network with multi-task pre-training. Specifically, we mask key sentences at the word-level encoder and generate them at the decoder. Besides, we randomly mask some of the role alignments in the input text and force the model to recover the original role tags to complete the alignments. In addition, we introduce a topic segmentation mechanism to further improve the quality of the generated summaries. The experimental results show that our model is superior to the previous methods in meeting summary datasets AMI and ICSI.
Curriculum learning, a machine training strategy that feeds training instances to the model from easy to hard, has been proven to facilitate the dialogue generation task. Meanwhile, knowledge distillation, a knowledge transformation methodology among
teachers and students networks can yield significant performance boost for student models. Hence, in this paper, we introduce a combination of curriculum learning and knowledge distillation for efficient dialogue generation models, where curriculum learning can help knowledge distillation from data and model aspects. To start with, from the data aspect, we cluster the training cases according to their complexity, which is calculated by various types of features such as sentence length and coherence between dialog pairs. Furthermore, we employ an adversarial training strategy to identify the complexity of cases from model level. The intuition is that, if a discriminator can tell the generated response is from the teacher or the student, then the case is difficult that the student model has not adapted to yet. Finally, we use self-paced learning, which is an extension to curriculum learning to assign weights for distillation. In conclusion, we arrange a hierarchical curriculum based on the above two aspects for the student model under the guidance from the teacher model. Experimental results demonstrate that our methods achieve improvements compared with competitive baselines.
Statistical language modeling and translation with transformers have found many successful applications in program understanding and generation tasks, setting high benchmarks for tools in modern software development environments. The finite context w
indow of these neural models means, however, that they will be unable to leverage the entire relevant context of large files and packages for any given task. While there are many efforts to extend the context window, we introduce an architecture-independent approach for leveraging the syntactic hierarchies of source code for incorporating entire file-level context into a fixed-length window. Using concrete syntax trees of each source file we extract syntactic hierarchies and integrate them into context window by selectively removing from view more specific, less relevant scopes for a given task. We evaluate this approach on code generation tasks and joint translation of natural language and source code in Python programming language, achieving a new state-of-the-art in code completion and summarization for Python in the CodeXGLUE benchmark. We also introduce new CodeXGLUE benchmarks for user-experience-motivated tasks: code completion with normalized literals, method body completion/code summarization conditioned on file-level context.
Recent work has raised concerns about the inherent limitations of text-only pretraining. In this paper, we first demonstrate that reporting bias, the tendency of people to not state the obvious, is one of the causes of this limitation, and then inves
tigate to what extent multimodal training can mitigate this issue. To accomplish this, we 1) generate the Color Dataset (CoDa), a dataset of human-perceived color distributions for 521 common objects; 2) use CoDa to analyze and compare the color distribution found in text, the distribution captured by language models, and a human's perception of color; and 3) investigate the performance differences between text-only and multimodal models on CoDa. Our results show that the distribution of colors that a language model recovers correlates more strongly with the inaccurate distribution found in text than with the ground-truth, supporting the claim that reporting bias negatively impacts and inherently limits text-only training. We then demonstrate that multimodal models can leverage their visual training to mitigate these effects, providing a promising avenue for future research.
Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and response time
, and with this purpose multiple latency measures have been proposed. However, latency evaluations for simultaneous translation are estimated at the sentence level, not taking into account the sequential nature of a streaming scenario. Indeed, these sentence-level latency measures are not well suited for continuous stream translation, resulting in figures that are not coherent with the simultaneous translation policy of the system being assessed. This work proposes a stream level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task.
SemEval is the primary venue in the NLP community for the proposal of new challenges and for the systematic empirical evaluation of NLP systems. This paper provides a systematic quantitative analysis of SemEval aiming to evidence the patterns of the
contributions behind SemEval. By understanding the distribution of task types, metrics, architectures, participation and citations over time we aim to answer the question on what is being evaluated by SemEval.
We present the results of the first task on Large-Scale Multilingual Machine Translation. The task consists on the many-to-many evaluation of a single model across a variety of source and target languages. This year, the task consisted on three diffe
rent settings: (i) SMALL-TASK1 (Central/South-Eastern European Languages), (ii) the SMALL-TASK2 (South-East Asian Languages), and (iii) FULL-TASK (all 101 x 100 language pairs). All the tasks used the FLORES-101 dataset as the evaluation benchmark. To ensure the longevity of the dataset, the test sets were not publicly released and the models were evaluated in a controlled environment on Dynabench. There were a total of 10 participating teams for the tasks, with a total of 151 intermediate model submissions and 13 final models. This year's result show a significant improvement over the known base-lines with +17.8 BLEU for SMALL-TASK2, +10.6 for FULL-TASK and +3.6 for SMALL-TASK1.
This paper describes Mininglamp neural machine translation systems of the WMT2021 news translation tasks. We have participated in eight directions translation tasks for news text including Chinese to/from English, Hausa to/from English, German to/fro
m English and French to/from German. Our fundamental system was based on Transformer architecture, with wider or smaller construction for different news translation tasks. We mainly utilized the method of back-translation, knowledge distillation and fine-tuning to boost single model, while the ensemble was used to combine single models. Our final submission has ranked first for the English to/from Hausa task.
This paper presents the University of Edinburgh's constrained submissions of English-German and English-Hausa systems to the WMT 2021 shared task on news translation. We build En-De systems in three stages: corpus filtering, back-translation, and fin
e-tuning. For En-Ha we use an iterative back-translation approach on top of pre-trained En-De models and investigate vocabulary embedding mapping.
We consider the hierarchical representation of documents as graphs and use geometric deep learning to classify them into different categories. While graph neural networks can efficiently handle the variable structure of hierarchical documents using t
he permutation invariant message passing operations, we show that we can gain extra performance improvements using our proposed selective graph pooling operation that arises from the fact that some parts of the hierarchy are invariable across different documents. We applied our model to classify clinical trial (CT) protocols into completed and terminated categories. We use bag-of-words based, as well as pre-trained transformer-based embeddings to featurize the graph nodes, achieving f1-scoresaround 0.85 on a publicly available large scale CT registry of around 360K protocols. We further demonstrate how the selective pooling can add insights into the CT termination status prediction. We make the source code and dataset splits accessible.
