Alessandro Sordoni

Siva Reddy

2022-02-28

ArXiv (preprint)

Multi-Head Adapter Routing for Data-Efficient Fine-Tuning

Lucas Caccia

Edoardo Ponti

Lu Liu

Matheus Pereira

Nicolas Le Roux

Parameter-efﬁcient ﬁne-tuning (PEFT) methods can adapt large language models to downstream tasks by training a small amount of newly add… (see more)ed parameters. In multi-task settings, PEFT adapters typically train on each task independently, inhibiting transfer across tasks, or on the concatenation of all tasks, which can lead to negative interference. To address this, Polytropon [Ponti et al., 2022] jointly learns an inventory of PEFT adapters and a routing function to share variable-size sets of adapters across tasks. Subsequently, adapters can be re-combined and ﬁne-tuned on novel tasks even with limited data. In this paper, we investigate to what extent the ability to control which adapters are active for each task leads to sample-efﬁcient generalization. Thus, we propose less expressive variants where we perform weighted averaging of the adapters before few-shot adaptation ( Poly - µ ) instead of learning a routing function. Moreover, we introduce more expressive variants where ﬁner-grained task–adapter allocation is learned through a multi-head routing function ( Poly - S ). We test these variants on three separate benchmarks for multi-task learning. We ﬁnd that Poly - S achieves gains on all three (up to 5.3 points on average) over strong baselines, while incurring a negligible additional cost in parameter count. In particular, we ﬁnd that instruction tuning, where models are fully ﬁne-tuned on natural language instructions for each task, is inferior to modular methods such as Polytropon and our proposed variants.

2022-01-01

arXiv.org (preprint)

Unsupervised Dependency Graph Network

Yikang Shen

Shawn Tan

Peng Li

Jie Zhou

Aaron Courville

Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, s… (see more)ome self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.

2022-01-01

Annual Meeting of the Association for Computational Linguistics (published)

Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge

Ian Porada

Jackie Cheung

Transformer models pre-trained with a masked-language-modeling objective (e.g., BERT) encode commonsense knowledge as evidenced by behaviora… (see more)l probes; however, the extent to which this knowledge is acquired by systematic inference over the semantics of the pre-training corpora is an open question. To answer this question, we selectively inject verbalized knowledge into the pre-training minibatches of BERT and evaluate how well the model generalizes to supported inferences after pre-training on the injected knowledge. We find generalization does not improve over the course of pre-training BERT from scratch, suggesting that commonsense knowledge is acquired from surface-level, co-occurrence patterns rather than induced, systematic reasoning.

2021-12-16

ArXiv (preprint)

Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle

Yikang Shen

Shawn Tan

Siva Reddy

Aaron Courville

Syntax is fundamental to our thinking about language. Failing to capture the structure of input language could lead to generalization proble… (see more)ms and over-parametrization. In the present work, we propose a new syntax-aware language model: Syntactic Ordered Memory (SOM). The model explicitly models the structure with an incremental parser and maintains the conditional probability setting of a standard language model (left-to-right). To train the incremental parser and avoid exposure bias, we also propose a novel dynamic oracle, so that SOM is more robust to wrong parsing decisions. Experiments show that SOM can achieve strong results in language modeling, incremental parsing, and syntactic generalization tests while using fewer parameters than other models.

2021-06-01

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (published)

Understanding by Understanding Not: Modeling Negation in Language Models

Arian Hosseini

Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language mode… (see more)ls often handle negation incorrectly. To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus. By training BERT with the resulting combined objective we reduce the mean top 1 error rate to 4% on the negated LAMA dataset. We also see some improvements on the negated NLI benchmarks.

2021-06-01

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (published)

Explicitly Modeling Syntax in Language Model improves Generalization

Yikang Shen

Shawn Tan

Siva Reddy

Aaron Courville

Syntax is fundamental to our thinking about language. Although neural networks are very successful in many tasks, they do not explicitly mod… (see more)el syntactic structure. Failing to capture the structure of inputs could lead to generalization problems and over-parametrization. In the present work, we propose a new syntax-aware language model: Syntactic Ordered Memory (SOM). The model explicitly models the structure with a one-step look-ahead parser and maintains the conditional probability setting of the standard language model. Experiments show that SOM can achieve strong results in language modeling and syntactic generalization tests, while using fewer parameters then other models.

2020-10-21

arXiv.org (preprint)

dblp.uni-trier.de

Focused Hierarchical RNNs for Conditional Sequence Processing

Nan Rosemary Ke

Konrad Żołna

Zhouhan Lin

Adam Trischler

Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most o… (see more)f these models use a simple form of encoder with attention that looks over the entire sequence and assigns a weight to each token independently. We present a mechanism for focusing RNN encoders for sequence modelling tasks which allows them to attend to key parts of the input as needed. We formulate this using a multi-layer conditional sequence encoder that reads in one token at a time and makes a discrete decision on whether the token is relevant to the context or question being asked. The discrete gating mechanism takes in the context embedding and the current hidden state as inputs and controls information flow into the layer above. We train it using policy gradient methods. We evaluate this method on several types of tasks with different attributes. First, we evaluate the method on synthetic tasks which allow us to evaluate the model for its generalization ability and probe the behavior of the gates in more controlled settings. We then evaluate this approach on large scale Question Answering tasks including the challenging MS MARCO and SearchQA tasks. Our models shows consistent improvements for both tasks over prior work and our baselines. It has also shown to generalize significantly better on synthetic tasks as compared to the baselines.

2018-07-03

Proceedings of the 35th International Conference on Machine Learning (published)

proceedings.mlr.press

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Iulian V. Serban

Ryan Lowe

Sequential data often possesses hierarchical structures with complex dependencies between sub-sequences, such as found between the utterance… (see more)s in a dialogue. To model these dependencies in a generative framework, we propose a neural network-based generative architecture, with stochastic latent variables that span a variable number of time steps. We apply the proposed model to the task of dialogue response generation and compare it with other recent neural-network architectures. We evaluate the model performance through a human evaluation study. The experiments demonstrate that our model improves upon recently proposed models and that the latent variables facilitate both the generation of meaningful, long and diverse responses and maintaining dialogue state.

2017-02-12

Proceedings of the AAAI Conference on Artificial Intelligence (published)