Implications of Annotation Artifacts in Edge Probing Test Datasets

Edge probing tests are classification tasks that test for grammatical knowledge encoded in token representations coming from contextual encoders such as large language models (LLMs). Many LLM encoders have shown high performance in EP tests, leading to conjectures about their ability to encode linguistic knowledge. However, a large body of research claims that the tests necessarily do not measure the LLM's capacity to encode knowledge, but rather reflect the classifiers' ability to learn the problem. Much of this criticism stems from the fact that often the classifiers have very similar accuracy when an LLM vs a random encoder is used. Consequently, several modifications to the tests have been suggested, including information theoretic probes. We show that commonly used edge probing test datasets have various biases including memorization. When these biases are removed, the LLM encoders do show a significant difference from the random ones, even with the simple non-information theoretic probes.

Explaining Interactions Between Text Spans

Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI). However, existing highlight-based explanations primarily focus on identifying individual important tokens or interactions only between adjacent tokens or tuples of tokens. Most notably, there is a lack of annotations capturing the human decision-making process w.r.t. the necessary interactions for informed decision-making in such tasks. To bridge this gap, we introduce SpanEx, a multi-annotator dataset of human span interaction explanations for two NLU tasks: NLI and FC. We then investigate the decision-making processes of multiple fine-tuned large language models in terms of the employed connections between spans in separate parts of the input and compare them to the human reasoning processes. Finally, we present a novel community detection based unsupervised method to extract such interaction explanations from a model's inner workings.

Machine Reading, Fast and Slow: When Do Models "Understand" Language?

Two of the most fundamental challenges in Natural Language Understanding (NLU) at present are: (a) how to establish whether deep learning-based models score highly on NLU benchmarks for the 'right' reasons; and (b) to understand what those reasons would even be. We investigate the behavior of reading comprehension models with respect to two linguistic 'skills': coreference resolution and comparison. We propose a definition for the reasoning steps expected from a system that would be 'reading slowly', and compare that with the behavior of five models of the BERT family of various sizes, observed through saliency scores and counterfactual explanations. We find that for comparison (but not coreference) the systems based on larger encoders are more likely to rely on the 'right' information, but even they struggle with generalization, suggesting that they still learn specific lexical patterns rather than the general principles of comparison.

Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?

There have been many efforts to try to understand what gram-matical knowledge (e.g., ability to understand the part of speech of a token) is encoded in large pre-trained language models (LM). This is done through 'Edge Probing' (EP) tests: simple ML models that predict the grammatical properties ofa span (whether it has a particular part of speech) using only the LM's token representations. However, most NLP applications use fine-tuned LMs. Here, we ask: if a LM is fine-tuned, does the encoding of linguistic information in it change, as measured by EP tests? Conducting experiments on multiple question-answering (QA) datasets, we answer that question negatively: the EP test results do not change significantly when the fine-tuned QA model performs well or in adversarial situations where the model is forced to learn wrong correlations. However, a critical analysis of the EP task datasets reveals that EP models may rely on spurious correlations to make predictions. This indicates even if fine-tuning changes the encoding of such knowledge, the EP tests might fail to measure it.

Intent Features for Rich Natural Language Understanding

Complex natural language understanding modules in dialog systems have a richer understanding of user utterances, and thus are critical in providing a better user experience. However, these models are often created from scratch, for specific clients and use cases, and require the annotation of large datasets. This encourages the sharing of annotated data across multiple clients. To facilitate this we introduce the idea of intent features: domain and topic agnostic properties of intents that can be learned from the syntactic cues only, and hence can be shared. We introduce a new neural network architecture, the Global-Local model, that shows significant improvement over strong baselines for identifying these features in a deployed, multi-intent natural language understanding module, and, more generally, in a classification setting where a part of an utterance has to be classified utilizing the whole context.

Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models

While the prevalence of large pre-trained language models has led to significant improvements in the performance of NLP systems, recent research has demonstrated that these models inherit societal biases extant in natural language. In this paper, we explore a simple method to probe pre-trained language models for gender bias, which we use to effect a multi-lingual study of gender bias towards politicians. We construct a dataset of 250k politicians from most countries in the world and quantify adjective and verb usage around those politicians' names as a function of their gender. We conduct our study in 7 languages across 6 different language modeling architectures. Our results demonstrate that stance towards politicians in pre-trained language models is highly dependent on the language used. Finally, contrary to previous findings, our study suggests that larger language models do not tend to be significantly more gender-biased than smaller ones.

Multiple Word Embeddings for Increased Diversity of Representation

Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand. The improvements afforded by these "contextual embeddings" come with a high computational cost. In this work, we explore a simple technique that substantially and consistently improves performance over a strong baseline with negligible increase in run time. We concatenate multiple pre-trained embeddings to strengthen our representation of words. We show that this concatenation technique works across many tasks, datasets, and model types. We analyze aspects of pre-trained embedding similarity and vocabulary coverage and find that the representational diversity between different pre-trained embeddings is the driving force of why this technique works. We provide open source implementations of our models in both TensorFlow and PyTorch.

Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers

Current state-of-the-art models for named entity recognition (NER) are neural models with a conditional random field (CRF) as the final layer. Entities are represented as per-token labels with a special structure in order to decode them into spans. Current work eschews prior knowledge of how the span encoding scheme works and relies on the CRF learning which transitions are illegal and which are not to facilitate global coherence. We find that by constraining the output to suppress illegal transitions we can train a tagger with a cross-entropy loss twice as fast as a CRF with differences in F1 that are statistically insignificant, effectively eliminating the need for a CRF. We analyze the dynamics of tag co-occurrence to explain when these constraints are most effective and provide open source implementations of our tagger in both PyTorch and TensorFlow.