Related papers: Nightmare at test time: How punctuation prevents p…

Evaluating translation models is a trade-off between effort and detail. On the one end of the spectrum there are automatic count-based methods such as BLEU, on the other end linguistic evaluations by humans, which arguably are more…

The paper shows that matching without replacement on propensity scores produces estimators that generally are inconsistent for the average treatment effect of the treated. To achieve consistency, practitioners must either assume that no…

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Humans are accustomed to environments that contain both regularities and exceptions. For example, at most gas stations, one pays prior to pumping, but the occasional rural station does not accept payment in advance. Likewise, deep neural…

Large language models improve at math after instruction tuning, reinforcement learning, or knowledge distillation. We ask whether these gains come from major changes in the transformer layers or from smaller adjustments that keep the…

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…

Ensuring proper punctuation and letter casing is a key pre-processing step towards applying complex natural language processing algorithms. This is especially significant for textual sources where punctuation and casing are missing, such as…

For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low…

This paper studies AI persuasion by distinguishing between two reasons for disagreement: attention differences, where the AI detects features the decision-maker missed, and comprehension differences, where the AI and the decision-maker…

Hallucinations in text generation occur when the system produces text that is not grounded in the input. In this work, we tackle the problem of hallucinations in neural chart summarization. Our analysis shows that the target side of chart…

AI-text detectors achieve high accuracy on in-domain benchmarks, but often struggle to generalize across different generation conditions such as unseen prompts, model families, or domains. While prior work has reported these generalization…

This paper presents an analysis of annotation using an automatic pre-annotation for a mid-level annotation complexity task -- dependency syntax annotation. It compares the annotation efforts made by annotators using a pre-annotated version…

This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus…

Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…

Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to…

Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of the posts, implicitly assuming that comments maybe judged…

Current speech translation systems, while having achieved impressive accuracies, are rather static in their behavior and do not adapt to real-world situations in ways human interpreters do. In order to improve their practical usefulness and…

The picture-word interference paradigm (participants name target pictures while ignoring distractor words) is often used to model the planning processes involved in word production. The participants' naming times are delayed in the presence…

Meaning is context-dependent, but many properties of language (should) remain the same even if we transform the context. For example, sentiment, entailment, or speaker properties should be the same in a translation and original of a text.…

The current state-of-the-art in many natural language processing and automated knowledge base completion tasks is held by representation learning methods which learn distributed vector representations of symbols via gradient-based…