Large Language Models (LLMs) have achieved remarkable success thanks to scalability on large text corpora, but have some drawback in training efficiency. In contrast, Syntactic Language Models (SLMs) can be trained efficiently to reach relatively high performance thanks to syntactic supervision, but have trouble with scalability. Thus, given these complementary advantages of LLMs and SLMs, it is necessary to develop an architecture that integrates the scalability of LLMs with the training efficiency of SLMs, namely Syntactic Large Language Models (SLLM). In this paper, we propose a novel method dubbed tree-planting: implicitly "plant" trees into attention weights of Transformer LMs to reflect syntactic structures of natural language. Specifically, Transformer LMs trained with tree-planting will be called Tree-Planted Transformers (TPT), which learn syntax on small treebanks via tree-planting and then scale on large text corpora via continual learning with syntactic scaffolding. Targeted syntactic evaluations on the SyntaxGym benchmark demonstrated that TPTs, despite the lack of explicit syntactic supervision, significantly outperformed various SLMs with explicit syntactic supervision that generate hundreds of syntactic structures in parallel, suggesting that tree-planting and TPTs are the promising foundation for SLLMs.
The world's languages exhibit certain so-called typological or implicational universals; for example, Subject-Object-Verb (SOV) word order typically employs postpositions. Explaining the source of such biases is a key goal in linguistics. We study the word-order universals through a computational simulation with language models (LMs). Our experiments show that typologically typical word orders tend to have lower perplexity estimated by LMs with cognitively plausible biases: syntactic biases, specific parsing strategies, and memory limitations. This suggests that the interplay of these cognitive biases and predictability (perplexity) can explain many aspects of word-order universals. This also showcases the advantage of cognitively-motivated LMs, which are typically employed in cognitive modeling, in the computational simulation of language universals.
Next-word probabilities from language models have been shown to successfully simulate human reading behavior. Building on this, we show that, interestingly, instruction-tuned large language models (LLMs) yield worse psychometric predictive power (PPP) for human reading behavior than base LLMs with equivalent perplexities. In other words, instruction tuning, which helps LLMs provide human-preferred responses, does not always make them human-like from the computational psycholinguistics perspective. In addition, we explore prompting methodologies in simulating human reading behavior with LLMs, showing that prompts reflecting a particular linguistic hypothesis lead LLMs to exhibit better PPP but are still worse than base LLMs. These highlight that recent instruction tuning and prompting do not offer better estimates than direct probability measurements from base LLMs in cognitive modeling.
Neural language models have exhibited outstanding performance in a range of downstream tasks. However, there is limited understanding regarding the extent to which these models internalize syntactic knowledge, so that various datasets have recently been constructed to facilitate syntactic evaluation of language models across languages. In this paper, we introduce JCoLA (Japanese Corpus of Linguistic Acceptability), which consists of 10,020 sentences annotated with binary acceptability judgments. Specifically, those sentences are manually extracted from linguistics textbooks, handbooks and journal articles, and split into in-domain data (86 %; relatively simple acceptability judgments extracted from textbooks and handbooks) and out-of-domain data (14 %; theoretically significant acceptability judgments extracted from journal articles), the latter of which is categorized by 12 linguistic phenomena. We then evaluate the syntactic knowledge of 9 different types of Japanese language models on JCoLA. The results demonstrated that several models could surpass human performance for the in-domain data, while no models were able to exceed human performance for the out-of-domain data. Error analyses by linguistic phenomena further revealed that although neural language models are adept at handling local syntactic dependencies like argument structure, their performance wanes when confronted with long-distance syntactic dependencies like verbal agreement and NPI licensing.
In this paper, we propose a novel architecture called Composition Attention Grammars (CAGs) that recursively compose subtrees into a single vector representation with a composition function, and selectively attend to previous structural information with a self-attention mechanism. We investigate whether these components -- the composition function and the self-attention mechanism -- can both induce human-like syntactic generalization. Specifically, we train language models (LMs) with and without these two components with the model sizes carefully controlled, and evaluate their syntactic generalization performance against six test circuits on the SyntaxGym benchmark. The results demonstrated that the composition function and the self-attention mechanism both play an important role to make LMs more human-like, and closer inspection of linguistic phenomenon implied that the composition function allowed syntactic features, but not semantic features, to percolate into subtree representations.
Do modern natural language processing (NLP) models exhibit human-like language processing? How can they be made more human-like? These questions are motivated by psycholinguistic studies for understanding human language processing as well as engineering efforts. In this study, we demonstrate the discrepancies in context access between modern neural language models (LMs) and humans in incremental sentence processing. Additional context limitation was needed to make LMs better simulate human reading behavior. Our analyses also showed that human-LM gaps in memory access are associated with specific syntactic constructions; incorporating additional syntactic factors into LMs' context access could enhance their cognitive plausibility.
In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investigated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed.
In computational psycholinguistics, various language models have been evaluated against human reading behavior (e.g., eye movement) to build human-like computational models. However, most previous efforts have focused almost exclusively on English, despite the recent trend towards linguistic universal within the general community. In order to fill the gap, this paper investigates whether the established results in computational psycholinguistics can be generalized across languages. Specifically, we re-examine an established generalization -- the lower perplexity a language model has, the more human-like the language model is -- in Japanese with typologically different structures from English. Our experiments demonstrate that this established generalization exhibits a surprising lack of universality; namely, lower perplexity is not always human-like. Moreover, this discrepancy between English and Japanese is further explored from the perspective of (non-)uniform information density. Overall, our results suggest that a cross-lingual evaluation will be necessary to construct human-like computational models.
As a language model that integrates traditional symbolic operations and flexible neural representations, recurrent neural network grammars (RNNGs) have attracted great attention from both scientific and engineering perspectives. However, RNNGs are known to be harder to scale due to the difficulty of batched training. In this paper, we propose effective batching for RNNGs, where every operation is computed in parallel with tensors across multiple sentences. Our PyTorch implementation effectively employs a GPU and achieves x6 speedup compared to the existing C++ DyNet implementation with model-independent auto-batching. Moreover, our batched RNNG also accelerates inference and achieves x20-150 speedup for beam search depending on beam sizes. Finally, we evaluate syntactic generalization performance of the scaled RNNG against the LSTM baseline, based on the large training data of 100M tokens from English Wikipedia and the broad-coverage targeted syntactic evaluation benchmark. Our RNNG implementation is available at https://github.com/aistairc/rnng-pytorch/.