The Berkeley Crossword Solver – The Berkeley Synthetic Intelligence Analysis Weblog

We just lately revealed the Berkeley Crossword Solver (BCS), the present state-of-the-art for fixing American-style crossword puzzles. The BCS combines neural query answering and probabilistic inference to attain near-perfect efficiency on most American-style crossword puzzles, just like the one proven under:

Determine 1: Instance American-style crossword puzzle

An earlier model of the BCS, together with Dr.Fill, was the primary laptop program to outscore all human rivals on the earth’s prime crossword match. The newest model is the present top-performing system on crossword puzzles from The New York Instances, attaining 99.7% letter accuracy (see the technical paper, internet demo, and code launch).

Crosswords are difficult for people and computer systems alike. Many clues are imprecise or underspecified and may’t be answered till crossing constraints are taken under consideration. Whereas some clues are just like factoid query answering, others require relational reasoning or understanding troublesome wordplay.

Listed below are a handful of instance clues from our dataset (solutions on the backside of this publish):

  • They’re given out at Berkeley’s HAAS College (4)
  • Winter hrs. in Berkeley (3)
  • Area ender that UC Berkeley was one of many first faculties to undertake (3)
  • Angeleno at Berkeley, say (8)

The BCS makes use of a two-step course of to unravel crossword puzzles. First, it generates a chance distribution over potential solutions to every clue utilizing a query answering (QA) mannequin; second, it makes use of probabilistic inference, mixed with native search and a generative language mannequin, to deal with conflicts between proposed intersecting solutions.

Determine 2: Structure diagram of the Berkeley Crossword Solver

The BCS’s query answering mannequin is predicated on DPR (Karpukhin et al., 2020), which is a bi-encoder mannequin usually used to retrieve passages which are related to a given query. Slightly than passages, nevertheless, our method maps each questions and solutions right into a shared embedding area and finds solutions straight. In comparison with the earlier state-of-the-art methodology for answering crossword clues, this method obtained a 13.4% absolute enchancment in top-1000 QA accuracy. We performed a guide error evaluation and located that our QA mannequin usually carried out nicely on questions involving data, commonsense reasoning, and definitions, nevertheless it typically struggled to know wordplay or theme-related clues.

After working the QA mannequin on every clue, the BCS runs crazy perception propagation to iteratively replace the reply chances within the grid. This enables info from excessive confidence predictions to propagate to tougher clues. After perception propagation converges, the BCS obtains an preliminary puzzle answer by greedily taking the very best chance reply at every place.

The BCS then refines this answer utilizing an area search that tries to exchange low confidence characters within the grid. Native search works by utilizing a guided proposal distribution during which characters that had decrease marginal chances throughout perception propagation are iteratively changed till a regionally optimum answer is discovered. We rating these alternate characters utilizing a character-level language mannequin (ByT5, Xue et al., 2022), that handles novel solutions higher than our closed-book QA mannequin.

Determine 3: Instance adjustments made by our native search process

We evaluated the BCS on puzzles from 5 main crossword publishers, together with The New York Instances. Our system obtains 99.7% letter accuracy on common, which jumps to 99.9% in the event you ignore puzzles that contain uncommon themes. It solves 81.7% of puzzles with out a single mistake, which is a 24.8% enchancment over the earlier state-of-the-art system.

Determine 4: Outcomes in comparison with earlier state-of-the-art Dr.Fill

The American Crossword Puzzle Match (ACPT) is the biggest and longest-running crossword match and is organized by Will Shortz, the New York Instances crossword editor. Two prior approaches to laptop crossword fixing gained mainstream consideration and competed within the ACPT: Proverb and Dr.Fill. Proverb is a 1998 system that ranked 213th out of 252 rivals within the match. Dr.Fill’s first competitors was in ACPT 2012, and it ranked 141st out of 650 rivals. We teamed up with Dr.Fill’s creator Matt Ginsberg and mixed an early model of our QA system with Dr.Fill’s search process to outscore all 1033 human rivals within the 2021 ACPT. Our joint submission solved all seven puzzles in below a minute, lacking simply three letters throughout two puzzles.

Determine 5: Outcomes from the 2021 American Crossword Puzzle Match (ACPT)

We’re actually excited concerning the challenges that stay in crosswords, together with dealing with troublesome themes and extra complicated wordplay. To encourage future work, we’re releasing a dataset of 6.4M query reply clues, a demo of the Berkeley Crossword Solver, and our code at

Solutions to clues: MBAS, PST, EDU, INSTATER

Latest articles

Related articles

Leave a reply

Please enter your comment!
Please enter your name here