Neural language models typically tokenise input text into sub-word units to achieve an open vocabulary. The standard approach is to use a single canonical tokenisation at both train and test time. We suggest that this approach is unsatisfactory and m
ay bottleneck our evaluation of language model performance. Using only the one-best tokenisation ignores tokeniser uncertainty over alternative tokenisations, which may hurt model out-of-domain performance. In this paper, we argue that instead, language models should be evaluated on their marginal likelihood over tokenisations. We compare different estimators for the marginal likelihood based on sampling, and show that it is feasible to estimate the marginal likelihood with a manageable number of samples. We then evaluate a pretrained language model on both the one-best-tokenisation and marginal perplexities, and show that the marginal perplexity can be significantly better than the one best, especially on out-of-domain data. We link this difference in perplexity to the tokeniser uncertainty as measured by tokeniser entropy. We discuss some implications of our results for language model training and evaluation, particularly with regard to tokenisation robustness.
Human evaluation has always been expensive while researchers struggle to trust the automatic metrics. To address this, we propose to customise traditional metrics by taking advantages of the pre-trained language models (PLMs) and the limited availabl
e human labelled scores. We first re-introduce the hLEPOR metric factors, followed by the Python version we developed (ported) which achieved the automatic tuning of the weighting parameters in hLEPOR metric. Then we present the customised hLEPOR (cushLEPOR) which uses Optuna hyper-parameter optimisation framework to fine-tune hLEPOR weighting parameters towards better agreement to pre-trained language models (using LaBSE) regarding the exact MT language pairs that cushLEPOR is deployed to. We also optimise cushLEPOR towards professional human evaluation data based on MQM and pSQM framework on English-German and Chinese-English language pairs. The experimental investigations show cushLEPOR boosts hLEPOR performances towards better agreements to PLMs like LABSE with much lower cost, and better agreements to human evaluations including MQM and pSQM scores, and yields much better performances than BLEU. Official results show that our submissions win three language pairs including English-German and Chinese-English on News domain via cushLEPOR(LM) and English-Russian on TED domain via hLEPOR. (data available at https://github.com/poethan/cushLEPOR)
Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the domain. Numerous real-world applications are based on domain-specific
text, e.g. working with financial or biomedical documents, and these applications often need to support multiple languages. However, large-scale domain-specific multilingual pretraining data for such scenarios can be difficult to obtain, due to regulations, legislation, or simply a lack of language- and domain-specific text. One solution is to train a single multilingual model, taking advantage of the data available in as many languages as possible. In this work, we explore the benefits of domain adaptive pretraining with a focus on adapting to multiple languages within a specific domain. We propose different techniques to compose pretraining corpora that enable a language model to both become domain-specific and multilingual. Evaluation on nine domain-specific datasets---for biomedical named entity recognition and financial sentence classification---covering seven different languages show that a single multilingual domain-specific model can outperform the general multilingual model, and performs close to its monolingual counterpart. This finding holds across two different pretraining methods, adapter-based pretraining and full model pretraining.
Code-mixed language plays a crucial role in communication in multilingual societies. Though the recent growth of web users has greatly boosted the use of such mixed languages, the current generation of dialog systems is primarily monolingual. This in
crease in usage of code-mixed language has prompted dialog systems in a similar language. We present our work in Code-Mixed Dialog Generation, an unexplored task in code-mixed languages, generating utterances in code-mixed language rather than a single language that is more often just English. We present a new synthetic corpus in code-mix for dialogs, CM-DailyDialog, by converting an existing English-only dialog corpus to a mixed Hindi-English corpus. We then propose a baseline approach where we show the effectiveness of using mBART like multilingual sequence-to-sequence transformers for code-mixed dialog generation. Our best performing dialog models can conduct coherent conversations in Hindi-English mixed language as evaluated by human and automatic metrics setting new benchmarks for the Code-Mixed Dialog Generation task.
We aim to automatically identify human action reasons in online videos. We focus on the widespread genre of lifestyle vlogs, in which people perform actions while verbally describing them. We introduce and make publicly available the WhyAct dataset,
consisting of 1,077 visual actions manually annotated with their reasons. We describe a multimodal model that leverages visual and textual information to automatically infer the reasons corresponding to an action presented in the video.
Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technology. To remedy for this, a wide
range of debiasing techniques have recently been introduced to remove such stereotypical biases from PLMs. Existing debiasing methods, however, directly modify all of the PLMs parameters, which -- besides being computationally expensive -- comes with the inherent risk of (catastrophic) forgetting of useful language knowledge acquired in pretraining. In this work, we propose a more sustainable modular debiasing approach based on dedicated debiasing adapters, dubbed ADELE. Concretely, we (1) inject adapter modules into the original PLM layers and (2) update only the adapters (i.e., we keep the original PLM parameters frozen) via language modeling training on a counterfactually augmented corpus. We showcase ADELE, in gender debiasing of BERT: our extensive evaluation, encompassing three intrinsic and two extrinsic bias measures, renders ADELE, very effective in bias mitigation. We further show that -- due to its modular nature -- ADELE, coupled with task adapters, retains fairness even after large-scale downstream training. Finally, by means of multilingual BERT, we successfully transfer ADELE, to six target languages.
Bias is pervasive for NLP models, motivating the development of automatic debiasing techniques. Evaluation of NLP debiasing methods has largely been limited to binary attributes in isolation, e.g., debiasing with respect to binary gender or race, how
ever many corpora involve multiple such attributes, possibly with higher cardinality. In this paper we argue that a truly fair model must consider gerrymandering' groups which comprise not only single attributes, but also intersectional groups. We evaluate a form of bias-constrained model which is new to NLP, as well an extension of the iterative nullspace projection technique which can handle multiple identities.
This paper describes Netmarble's submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. First, we propose a Curriculum Training Strategy in training stages. Facebook Fair's WMT19 news translation model was
chosen to engage the large and powerful pre-trained neural networks. Then, we post-train the translation model with different levels of data at each training stages. As the training stages go on, we make the system learn to solve multiple tasks by adding extra information at different training stages gradually. We also show a way to utilize the additional data in large volume for APE tasks. For further improvement, we apply Multi-Task Learning Strategy with the Dynamic Weight Average during the fine-tuning stage. To fine-tune the APE corpus with limited data, we add some related subtasks to learn a unified representation. Finally, for better performance, we leverage external translations as augmented machine translation (MT) during the post-training and fine-tuning. As experimental results show, our APE system significantly improves the translations of provided MT results by -2.848 and +3.74 on the development dataset in terms of TER and BLEU, respectively. It also demonstrates its effectiveness on the test dataset with higher quality than the development dataset.
Mikolov et al. (2013a) observed that continuous bag-of-words (CBOW) word embeddings tend to underperform Skip-gram (SG) embeddings, and this finding has been reported in subsequent works. We find that these observations are driven not by fundamental
differences in their training objectives, but more likely on faulty negative sampling CBOW implementations in popular libraries such as the official implementation, word2vec.c, and Gensim. We show that after correcting a bug in the CBOW gradient update, one can learn CBOW word embeddings that are fully competitive with SG on various intrinsic and extrinsic tasks, while being many times faster to train.
Popular dialog datasets such as MultiWOZ are created by providing crowd workers an instruction, expressed in natural language, that describes the task to be accomplished. Crowd workers play the role of a user and an agent to generate dialogs to accom
plish tasks involving booking restaurant tables, calling a taxi etc. In this paper, we present a data creation strategy that uses the pre-trained language model, GPT2, to simulate the interaction between crowd workers by creating a user bot and an agent bot. We train the simulators using a smaller percentage of actual crowd-generated conversations and their corresponding instructions. We demonstrate that by using the simulated data, we achieve significant improvements in low-resource settings on two publicly available datasets - MultiWOZ dataset and the Persona chat dataset.
