Quality Estimation (QE) models have the potential to change how we evaluate and maybe even train machine translation models. However, these models still lack the robustness to achieve general adoption. We show that Stateof-the-art QE models, when tested in a Parallel Corpus Mining (PCM) setting, perform unexpectedly bad due to a lack of robustness to out-of-domain examples. We propose a combination of multitask training, data augmentation and contrastive learning to achieve better and more robust QE performance. We show that our method improves QE performance significantly in the MLQE challenge and the robustness of QE models when tested in the Parallel Corpus Mining setup. We increase the accuracy in PCM by more than 0.80, making it on par with state-of-the-art PCM methods that use millions of sentence pairs to train their models. In comparison, we use a thousand times less data, 7K parallel sentences in total, and propose a novel low resource PCM method.

Large language models trained on a mixture of NLP tasks that are converted into a text-to-text format using prompts, can generalize into novel forms of language and handle novel tasks. A large body of work within prompt engineering attempts to understand the effects of input forms and prompts in achieving superior performance. We consider an alternative measure and inquire whether the way in which an input is encoded affects social biases promoted in outputs. In this paper, we study T0, a large-scale multi-task text-to-text language model trained using prompt-based learning. We consider two different forms of semantically equivalent inputs: question-answer format and premise-hypothesis format. We use an existing bias benchmark for the former BBQ and create the first bias benchmark in natural language inference BBNLI with hand-written hypotheses while also converting each benchmark into the other form. The results on two benchmarks suggest that given two different formulations of essentially the same input, T0 conspicuously acts more biased in question answering form, which is seen during training, compared to premise-hypothesis form which is unlike its training examples. Code and data are released under https://github.com/feyzaakyurek/bbnli.

The explosion of user-generated content (UGC)—e.g. social media posts and comments and and reviews—has motivated the development of NLP applications tailored to these types of informal texts. Prevalent among these applications have been sentiment analysis and machine translation (MT). Grounded in the observation that UGC features highly idiomatic and sentiment-charged language and we propose a decoder-side approach that incorporates automatic sentiment scoring into the MT candidate selection process. We train monolingual sentiment classifiers in English and Spanish and in addition to a multilingual sentiment model and by fine-tuning BERT and XLM-RoBERTa. Using n-best candidates generated by a baseline MT model with beam search and we select the candidate that minimizes the absolute difference between the sentiment score of the source sentence and that of the translation and and perform two human evaluations to assess the produced translations. Unlike previous work and we select this minimally divergent translation by considering the sentiment scores of the source sentence and translation on a continuous interval and rather than using e.g. binary classification and allowing for more fine-grained selection of translation candidates. The results of human evaluations show that and in comparison to the open-source MT baseline model on top of which our sentiment-based pipeline is built and our pipeline produces more accurate translations of colloquial and sentiment-heavy source texts.

At the intersection between computer vision and natural language processing, there has been recent progress on two natural language generation tasks: Dense Image Captioning and Referring Expression Generation for objects in complex scenes. The former aims to provide a caption for a specified object in a complex scene for the benefit of an interlocutor who may not be able to see it. The latter aims to produce a referring expression that will serve to identify a given object in a scene that the interlocutor can see. The two tasks are designed for different assumptions about the common ground between the interlocutors, and serve very different purposes, although they both associate a linguistic description with an object in a complex scene. Despite these fundamental differences, the distinction between these two tasks is sometimes overlooked. Here, we undertake a side-by-side comparison between image captioning and reference game human datasets and show that they differ systematically with respect to informativity. We hope that an understanding of the systematic differences among these human datasets will ultimately allow them to be leveraged more effectively in the associated engineering tasks.