Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned bilingual lexicons or on distribution matching, often with an assumption about the isometry of the two spaces. We propose a technique to quantitatively estimate this assumption of the isometry between two embedding spaces and empirically show that this assumption weakens as the languages in question become increasingly etymologically distant. We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) -a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique. Our proposed method obtains state of the art results on 15 of 18 language pairs on the MUSE dataset, and does particularly well when the embedding spaces don't appear to be isometric. In addition, we also show that adding supervision stabilizes the learning procedure, and is effective even with minimal supervision. *

We present the novel task of understanding multi-sentence entity-seeking questions (MSEQs), that is, the questions that may be expressed in multiple sentences, and that expect one or more entities as an answer. We formulate the problem of understanding MSEQs as a semantic labeling task over an open representation that makes minimal assumptions about schema or ontology-specific semantic vocabulary. At the core of our model, we use a BiLSTM (bidirectional LSTM) conditional random field (CRF), and to overcome the challenges of operating with low training data, we supplement it by using BERT embeddings, hand-designed features, as well as hard and soft constraints spanning multiple sentences. We find that this results in a 12–15 points gain over a vanilla BiLSTM CRF. We demonstrate the strengths of our work using the novel task of answering real-world entity-seeking questions from the tourism domain. The use of our labels helps answer 36% more questions with 35% more (relative) accuracy as compared to baselines. We also demonstrate how our framework can rapidly enable the parsing of MSEQs in an entirely new domain with small amounts of training data and little change in the semantic representation.

Modern pretrained language models are critical components of NLP pipelines. Yet, they suffer from spurious correlations, poor out-ofdomain generalization, and biases. Inspired by recent progress in causal machine learning, in particular the invariant risk minimization (IRM) paradigm, we propose invariant language modeling, a framework for learning invariant representations that generalize better across multiple environments. In particular, we adapt a game-theoretic implementation of IRM (IRM-games) to language models, where the invariance emerges from a specific training schedule in which all the environments compete to optimize their own environment-specific loss by updating subsets of the model in a round-robin fashion. In a series of controlled experiments, we demonstrate the ability of our method to (i) remove structured noise, (ii) ignore specific spurious correlations without affecting global performance, and (iii) achieve better out-of-domain generalization. These benefits come with a negligible computational overhead compared to standard training, do not require changing the local loss, and can be applied to any language model architecture. We believe this framework is promising to help mitigate spurious correlations and biases in language models.

Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations. However, learning such a routing mechanism encourages token clustering around expert centroids, implying a trend toward representation collapse. In this work, we propose to estimate the routing scores between tokens and experts on a lowdimensional hypersphere. We conduct extensive experiments on cross-lingual language model pre-training and fine-tuning on downstream tasks. Experimental results across seven multilingual benchmarks show that our method achieves consistent gains. We also present a comprehensive analysis on the representation and routing behaviors of our models. Our method alleviates the representation collapse issue and achieves more consistent routing than the baseline mixture-of-experts methods.

No abstract